NARC puzzles are designed so that neither the grid sequence nor the narrative clue is sufficient on its own — but together they uniquely determine the answer. The experiments below probe different dimensions of this narrative–visual interaction. Masking tests whether models can reconstruct hidden grids. Ordering tests whether narratives help recover temporal structure. Odd-one-out tests whether narratives help models recognize which grids belong together. Stances tests how the same visual pattern responds to different narrative framings. NARC-tiny runs the masking test on puzzles that a program generated from children's stories.
How to read this page. Masking is the documented battery: every active puzzle, all current models, order and keyword ablations; a paper on it is under review (September 2026). Ordering, Odd-one-out and Stances are pilot designs from spring 2026; each states its own scope and dates below. NARC-tiny is a separate set of generated puzzles with the same battery; it is not counted in the Masking tab. Counts are per model. The NARC property is a relation between a puzzle and a model, so a model with more NARC puzzles is not a better or worse model, and this page is not a leaderboard.
Ordering experiment: All grids are shown (unmasked) in a shuffled order. The model must recover the correct chronological sequence. Tested under two conditions: grids only and grids + narrative. Agreement with the true order is measured by Kendall's τ (−1 = reversed, 0 = random, +1 = perfect). Narrative lift = τ with narrative minus τ without.
τ = Kendall's tau correlation Lift = τ(grids+narrative) − τ(grids only) Positive lift = narrative helps ordering
Pilot. 11 models, 244 puzzles with four or more grids, data collected April 3, 2026 to October 8, 2026. Not re-run since and not part of the paper's claims. Report: Can Narratives Help AI Recover the Order of Events? (April 3, 2026, in the code repository).
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | -1.000 | +0.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 0.333 | +1.333 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 0.667 | +1.667 |
| gemma-4-31b | -0.667 | 1.000 | +1.667 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -0.333 | 1.000 | +1.333 |
| gpt-oss-20b | 0.000 | 0.667 | +0.667 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -0.667 | 1.000 | +1.667 |
| nemotron-3-super | -0.667 | 1.000 | +1.667 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -0.667 | 1.000 | +1.667 |
| nemotron-3-super | -0.667 | 0.667 | +1.334 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.867 | 0.467 | +1.334 |
| gemma-4-31b | -0.867 | 0.867 | +1.734 |
| glm-5.3-flash | -0.467 | 0.867 | +1.334 |
| gpt-oss-120b | -0.333 | 0.867 | +1.200 |
| gpt-oss-20b | -0.867 | 0.600 | +1.467 |
| kimi-k3 | -0.867 | 0.867 | +1.734 |
| mimo-v2.6-flash | -0.867 | 0.867 | +1.734 |
| nemotron-3-super | -0.467 | 0.867 | +1.334 |
| qwen3.5-122b | -0.867 | 0.867 | +1.734 |
| qwen3.6-27b | -0.867 | 0.867 | +1.734 |
| qwen3.8-27b | -0.867 | 0.867 | +1.734 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | -1.000 | +0.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 0.800 | +1.800 |
| gemma-4-31b | -0.800 | 0.800 | +1.600 |
| glm-5.3-flash | 0.000 | 0.600 | +0.600 |
| gpt-oss-120b | -0.800 | 1.000 | +1.800 |
| gpt-oss-20b | -0.600 | 1.000 | +1.600 |
| kimi-k3 | -0.800 | 1.000 | +1.800 |
| mimo-v2.6-flash | 0.000 | 0.600 | +0.600 |
| nemotron-3-super | -0.600 | 1.000 | +1.600 |
| qwen3.5-122b | -0.800 | 1.000 | +1.800 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -0.800 | 1.000 | +1.800 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 0.667 | +1.667 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -0.333 | 1.000 | +1.333 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -0.667 | 0.667 | +1.334 |
| nemotron-3-super | -0.333 | 1.000 | +1.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | -0.071 | 0.929 | +1.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -0.929 | -0.071 | +0.858 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.667 | 1.000 | +1.667 |
| gemma-4-31b | -0.333 | 1.000 | +1.333 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -0.333 | 1.000 | +1.333 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 1.000 | 0.667 | -0.333 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 0.000 | +1.000 |
| glm-5.3-flash | -1.000 | 0.667 | +1.667 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | -0.667 | 1.000 | +1.667 |
| qwen3.5-122b | -1.000 | 0.000 | +1.000 |
| qwen3.6-27b | -1.000 | 0.000 | +1.000 |
| qwen3.8-27b | -1.000 | 0.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | -1.000 | 0.000 | +1.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | -0.667 | -1.334 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | -0.667 | 0.000 | +0.667 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -0.667 | 1.000 | +1.667 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.000 | 0.333 | +0.333 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -1.000 | 0.667 | +1.667 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 0.000 | +1.000 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.333 | 1.000 | +0.667 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.400 | 1.000 | +1.400 |
| gemma-4-31b | -0.400 | 1.000 | +1.400 |
| glm-5.3-flash | -0.800 | 1.000 | +1.800 |
| gpt-oss-120b | -0.400 | 1.000 | +1.400 |
| gpt-oss-20b | -0.400 | 0.000 | +0.400 |
| kimi-k3 | -0.400 | 1.000 | +1.400 |
| mimo-v2.6-flash | -0.200 | 1.000 | +1.200 |
| nemotron-3-super | -0.400 | 1.000 | +1.400 |
| qwen3.5-122b | -0.400 | 1.000 | +1.400 |
| qwen3.6-27b | -0.400 | 1.000 | +1.400 |
| qwen3.8-27b | -0.400 | 1.000 | +1.400 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.667 | -1.000 | -0.333 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -0.333 | 1.000 | +1.333 |
| nemotron-3-super | -0.333 | -0.333 | +0.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | -0.667 | +0.333 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -0.667 | 1.000 | +1.667 |
| gpt-oss-120b | -0.667 | 1.000 | +1.667 |
| gpt-oss-20b | -0.667 | 0.000 | +0.667 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 0.667 | +1.667 |
| nemotron-3-super | 0.000 | 0.333 | +0.333 |
| qwen3.5-122b | -0.667 | -1.000 | -0.333 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.600 | 1.000 | +1.600 |
| gemma-4-31b | -0.800 | 1.000 | +1.800 |
| glm-5.3-flash | -0.800 | 1.000 | +1.800 |
| gpt-oss-120b | -0.200 | 1.000 | +1.200 |
| gpt-oss-20b | -0.600 | 0.000 | +0.600 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | -0.400 | 1.000 | +1.400 |
| nemotron-3-super | -0.400 | -0.400 | +0.000 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | -0.800 | 1.000 | +1.800 |
| qwen3.8-27b | -0.200 | 1.000 | +1.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | -0.667 | 1.000 | +1.667 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.400 | 0.200 | +0.600 |
| gemma-4-31b | -0.400 | 1.000 | +1.400 |
| glm-5.3-flash | -0.400 | 1.000 | +1.400 |
| gpt-oss-120b | -0.400 | 1.000 | +1.400 |
| gpt-oss-20b | -0.400 | 1.000 | +1.400 |
| kimi-k3 | -0.400 | 1.000 | +1.400 |
| mimo-v2.6-flash | -0.400 | 1.000 | +1.400 |
| nemotron-3-super | -0.400 | 0.200 | +0.600 |
| qwen3.5-122b | -0.400 | 0.200 | +0.600 |
| qwen3.6-27b | -0.400 | 1.000 | +1.400 |
| qwen3.8-27b | -0.400 | 1.000 | +1.400 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | -0.333 | -0.333 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -0.333 | 0.333 | +0.666 |
| nemotron-3-super | -0.333 | 0.000 | +0.333 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | -0.400 | 1.000 | +1.400 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -0.200 | 1.000 | +1.200 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | -0.200 | 1.000 | +1.200 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | -0.200 | 1.000 | +1.200 |
| gpt-oss-20b | -0.200 | 1.000 | +1.200 |
| kimi-k3 | -0.200 | 1.000 | +1.200 |
| mimo-v2.6-flash | -0.200 | 1.000 | +1.200 |
| nemotron-3-super | -0.200 | 1.000 | +1.200 |
| qwen3.5-122b | -0.200 | 1.000 | +1.200 |
| qwen3.6-27b | 0.200 | 1.000 | +0.800 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 0.667 | +1.000 |
| gemma-4-31b | -0.333 | 0.333 | +0.666 |
| glm-5.3-flash | -0.333 | 1.000 | +1.333 |
| gpt-oss-120b | -0.333 | 1.000 | +1.333 |
| kimi-k3 | -0.333 | 1.000 | +1.333 |
| mimo-v2.6-flash | -0.333 | -0.333 | +0.000 |
| nemotron-3-super | -0.333 | 1.000 | +1.333 |
| qwen3.5-122b | -0.333 | 1.000 | +1.333 |
| qwen3.6-27b | -0.333 | 1.000 | +1.333 |
| qwen3.8-27b | -0.333 | 1.000 | +1.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | -1.000 | -0.333 | +0.667 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 0.667 | +1.667 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -1.000 | 0.667 | +1.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 0.800 | +1.800 |
| gemma-4-31b | -0.400 | 1.000 | +1.400 |
| glm-5.3-flash | 0.000 | 0.800 | +0.800 |
| gpt-oss-120b | -0.400 | 1.000 | +1.400 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.200 | 1.000 | +0.800 |
| mimo-v2.6-flash | -0.400 | 0.000 | +0.400 |
| nemotron-3-super | -0.600 | 1.000 | +1.600 |
| qwen3.5-122b | 0.000 | 0.800 | +0.800 |
| qwen3.6-27b | 0.000 | 0.800 | +0.800 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | -0.333 | 1.000 | +1.333 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.333 | 1.000 | +0.667 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.333 | 1.000 | +0.667 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 0.667 | +1.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | -0.333 | 1.000 | +1.333 |
| gpt-oss-120b | -0.333 | 1.000 | +1.333 |
| kimi-k3 | -0.333 | 1.000 | +1.333 |
| mimo-v2.6-flash | 0.333 | 0.667 | +0.334 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | -0.333 | 1.000 | +1.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.467 | 0.067 | +0.534 |
| gemma-4-31b | -0.733 | 0.200 | +0.933 |
| glm-5.3-flash | 0.200 | 0.867 | +0.667 |
| gpt-oss-120b | -0.733 | 0.867 | +1.600 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | -0.333 | 1.000 | +1.333 |
| mimo-v2.6-flash | -0.733 | 1.000 | +1.733 |
| nemotron-3-super | -0.333 | 0.867 | +1.200 |
| qwen3.5-122b | -0.733 | 0.333 | +1.066 |
| qwen3.6-27b | -0.200 | -0.867 | -0.667 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.000 | 0.333 | +0.333 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.600 | 0.000 | +0.600 |
| gemma-4-31b | -0.400 | 1.000 | +1.400 |
| glm-5.3-flash | 0.000 | 0.800 | +0.800 |
| gpt-oss-120b | -0.200 | 1.000 | +1.200 |
| gpt-oss-20b | -0.800 | 0.000 | +0.800 |
| kimi-k3 | 0.200 | 1.000 | +0.800 |
| mimo-v2.6-flash | -0.800 | 0.000 | +0.800 |
| nemotron-3-super | -0.400 | 0.800 | +1.200 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.200 | 1.000 | +0.800 |
| qwen3.8-27b | 0.200 | 0.800 | +0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 0.333 | +0.666 |
| gemma-4-31b | -0.333 | 1.000 | +1.333 |
| glm-5.3-flash | -0.333 | 1.000 | +1.333 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | -0.333 | 1.000 | +1.333 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.000 | 0.333 | +0.333 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.333 | 1.000 | +0.667 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | 0.333 | 1.000 | +0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | -0.667 | 1.000 | +1.667 |
| qwen3.8-27b | -0.667 | 1.000 | +1.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | -1.000 | +0.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | -1.000 | -1.000 | +0.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 0.000 | +0.333 |
| gemma-4-31b | -0.333 | 1.000 | +1.333 |
| glm-5.3-flash | -0.667 | 0.000 | +0.667 |
| gpt-oss-120b | 1.000 | 0.333 | -0.667 |
| gpt-oss-20b | -0.667 | 0.000 | +0.667 |
| kimi-k3 | -0.667 | 1.000 | +1.667 |
| mimo-v2.6-flash | -0.667 | 0.667 | +1.334 |
| nemotron-3-super | -0.333 | -0.333 | +0.000 |
| qwen3.5-122b | -0.667 | 0.667 | +1.334 |
| qwen3.6-27b | -0.667 | 1.000 | +1.667 |
| qwen3.8-27b | -0.667 | 1.000 | +1.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.333 | 1.000 | +0.667 |
| nemotron-3-super | 0.333 | 1.000 | +0.667 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | -0.333 | 1.000 | +1.333 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | -0.667 | 0.667 | +1.334 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -1.000 | -0.333 | +0.667 |
| nemotron-3-super | -0.667 | 0.000 | +0.667 |
| qwen3.5-122b | -1.000 | 0.667 | +1.667 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 1.000 | +0.600 |
| gemma-4-31b | 0.400 | 1.000 | +0.600 |
| glm-5.3-flash | -0.400 | 1.000 | +1.400 |
| gpt-oss-120b | 0.200 | 1.000 | +0.800 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | -0.600 | 1.000 | +1.600 |
| mimo-v2.6-flash | 0.400 | 1.000 | +0.600 |
| nemotron-3-super | -0.600 | 1.000 | +1.600 |
| qwen3.5-122b | 0.400 | 1.000 | +0.600 |
| qwen3.6-27b | 0.600 | 1.000 | +0.400 |
| qwen3.8-27b | 0.600 | 1.000 | +0.400 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.733 | 0.467 | +1.200 |
| gemma-4-31b | -0.733 | 0.467 | +1.200 |
| glm-5.3-flash | 0.733 | 0.600 | -0.133 |
| gpt-oss-120b | -0.733 | 0.600 | +1.333 |
| gpt-oss-20b | -0.733 | -0.467 | +0.266 |
| kimi-k3 | -0.200 | 0.600 | +0.800 |
| mimo-v2.6-flash | -0.200 | 0.600 | +0.800 |
| nemotron-3-super | -0.867 | 0.600 | +1.467 |
| qwen3.5-122b | -0.733 | 0.600 | +1.333 |
| qwen3.6-27b | -0.733 | 0.600 | +1.333 |
| qwen3.8-27b | 0.733 | 0.600 | -0.133 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.800 | 0.200 | +1.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | -0.600 | 1.000 | +1.600 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | -0.800 | 1.000 | +1.800 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.600 | 1.000 | +1.600 |
| gemma-4-31b | -0.600 | 1.000 | +1.600 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | -0.400 | 1.000 | +1.400 |
| gpt-oss-20b | 0.000 | 0.600 | +0.600 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.800 | 1.000 | +0.200 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 0.800 | 0.400 | -0.400 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 0.333 | +0.333 |
| gemma-4-31b | 0.000 | 0.333 | +0.333 |
| glm-5.3-flash | -1.000 | 0.000 | +1.000 |
| gpt-oss-120b | 0.000 | 0.667 | +0.667 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.000 | 0.667 | +0.667 |
| nemotron-3-super | -0.667 | 0.667 | +1.334 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.667 | 1.000 | +0.333 |
| nemotron-3-super | 0.333 | 1.000 | +0.667 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.810 | 0.000 | +0.810 |
| gemma-4-31b | 0.714 | 0.714 | +0.000 |
| glm-5.3-flash | -0.905 | 0.619 | +1.524 |
| gpt-oss-120b | -0.333 | 0.524 | +0.857 |
| gpt-oss-20b | -0.333 | -0.048 | +0.285 |
| kimi-k3 | 0.714 | 0.619 | -0.095 |
| mimo-v2.6-flash | 0.714 | 0.619 | -0.095 |
| nemotron-3-super | -0.905 | 0.619 | +1.524 |
| qwen3.5-122b | -0.905 | 0.619 | +1.524 |
| qwen3.6-27b | -0.905 | 0.619 | +1.524 |
| qwen3.8-27b | -0.429 | 0.619 | +1.048 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | 1.000 | 0.800 | -0.200 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.733 | 0.467 | +1.200 |
| gemma-4-31b | -0.733 | 0.733 | +1.466 |
| glm-5.3-flash | -0.733 | 0.600 | +1.333 |
| gpt-oss-120b | 0.733 | 0.600 | -0.133 |
| gpt-oss-20b | -0.600 | 0.600 | +1.200 |
| kimi-k3 | 0.733 | 0.600 | -0.133 |
| mimo-v2.6-flash | -0.733 | 0.467 | +1.200 |
| nemotron-3-super | 0.733 | 0.733 | +0.000 |
| qwen3.5-122b | 0.733 | 0.600 | -0.133 |
| qwen3.6-27b | -0.733 | 0.600 | +1.333 |
| qwen3.8-27b | -0.733 | 0.600 | +1.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 1.000 | +0.667 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 0.333 | 1.000 | +0.667 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | -0.667 | 0.000 | +0.667 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | 0.333 | 1.000 | +0.667 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.333 | 1.000 | +0.667 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | -0.200 | 1.000 | +1.200 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.800 | 0.800 | +0.000 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 0.400 | +0.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.200 | 1.000 | +0.800 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.400 | 1.000 | +0.600 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | -0.600 | 1.000 | +1.600 |
| nemotron-3-super | 0.400 | 0.600 | +0.200 |
| qwen3.5-122b | 0.000 | -0.200 | -0.200 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | -0.400 | 1.000 | +1.400 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 1.000 | +0.600 |
| gemma-4-31b | 0.400 | 1.000 | +0.600 |
| glm-5.3-flash | -0.800 | 1.000 | +1.800 |
| gpt-oss-120b | 0.400 | 1.000 | +0.600 |
| gpt-oss-20b | -0.400 | 1.000 | +1.400 |
| kimi-k3 | 0.400 | 1.000 | +0.600 |
| mimo-v2.6-flash | 0.400 | 1.000 | +0.600 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 0.400 | 1.000 | +0.600 |
| qwen3.6-27b | 0.400 | 1.000 | +0.600 |
| qwen3.8-27b | 0.400 | 1.000 | +0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.600 | 0.800 | +1.400 |
| gemma-4-31b | -0.600 | -0.600 | +0.000 |
| glm-5.3-flash | -0.600 | 0.800 | +1.400 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.000 | 0.800 | +0.800 |
| kimi-k3 | 0.000 | 0.800 | +0.800 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | -0.600 | -0.800 | -0.200 |
| qwen3.5-122b | 0.000 | 0.800 | +0.800 |
| qwen3.6-27b | 0.800 | 1.000 | +0.200 |
| qwen3.8-27b | 0.000 | 0.800 | +0.800 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 0.667 | +1.000 |
| gemma-4-31b | -0.333 | 0.000 | +0.333 |
| glm-5.3-flash | -0.333 | 1.000 | +1.333 |
| gpt-oss-120b | -0.333 | 1.000 | +1.333 |
| gpt-oss-20b | 0.667 | 0.667 | +0.000 |
| kimi-k3 | -0.333 | 1.000 | +1.333 |
| mimo-v2.6-flash | 0.333 | -0.333 | -0.666 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | -0.333 | 0.333 | +0.666 |
| qwen3.6-27b | -0.333 | 1.000 | +1.333 |
| qwen3.8-27b | -0.333 | 0.667 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.067 | 0.067 | +0.000 |
| gemma-4-31b | -0.200 | 0.067 | +0.267 |
| glm-5.3-flash | -0.333 | 1.000 | +1.333 |
| gpt-oss-120b | -0.067 | 1.000 | +1.067 |
| gpt-oss-20b | 0.067 | 1.000 | +0.933 |
| kimi-k3 | 0.200 | 1.000 | +0.800 |
| mimo-v2.6-flash | 0.200 | 1.000 | +0.800 |
| nemotron-3-super | 0.333 | 0.600 | +0.267 |
| qwen3.5-122b | 0.333 | 1.000 | +0.667 |
| qwen3.6-27b | 0.067 | 1.000 | +0.933 |
| qwen3.8-27b | 0.333 | 1.000 | +0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 0.000 | +1.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | -1.000 | 0.000 | +1.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 1.000 | +1.333 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.000 | 0.000 | +0.000 |
| gpt-oss-20b | 0.000 | 0.333 | +0.333 |
| kimi-k3 | 0.000 | 0.000 | +0.000 |
| mimo-v2.6-flash | 0.000 | 0.000 | +0.000 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.800 | 0.200 | +1.000 |
| gemma-4-31b | -0.800 | 0.200 | +1.000 |
| glm-5.3-flash | -0.400 | 0.200 | +0.600 |
| gpt-oss-120b | -0.400 | 0.200 | +0.600 |
| gpt-oss-20b | 0.200 | 0.200 | +0.000 |
| kimi-k3 | -0.800 | 0.200 | +1.000 |
| mimo-v2.6-flash | -0.600 | 0.400 | +1.000 |
| nemotron-3-super | -0.800 | 0.200 | +1.000 |
| qwen3.5-122b | -0.800 | 0.200 | +1.000 |
| qwen3.6-27b | 0.400 | 0.200 | -0.200 |
| qwen3.8-27b | -0.400 | 0.200 | +0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | -0.200 | -0.200 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | -0.400 | 1.000 | +1.400 |
| gpt-oss-20b | -0.200 | -0.400 | -0.200 |
| kimi-k3 | -0.200 | 1.000 | +1.200 |
| mimo-v2.6-flash | -0.200 | 0.400 | +0.600 |
| nemotron-3-super | 0.200 | 0.600 | +0.400 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | -0.200 | 0.400 | +0.600 |
| qwen3.8-27b | 0.200 | 1.000 | +0.800 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 0.667 | +1.667 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 0.667 | 0.667 | +0.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | -1.000 | 0.333 | +1.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.000 | 0.333 | +0.333 |
| nemotron-3-super | 0.333 | 1.000 | +0.667 |
| qwen3.5-122b | 0.333 | 1.000 | +0.667 |
| qwen3.6-27b | 0.000 | 1.000 | +1.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.333 | 1.000 | +0.667 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.333 | 1.000 | +0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.667 | 0.667 | +1.334 |
| gemma-4-31b | 0.333 | 0.333 | +0.000 |
| glm-5.3-flash | 0.000 | 0.667 | +0.667 |
| gpt-oss-120b | 0.000 | 0.667 | +0.667 |
| gpt-oss-20b | -0.333 | 0.000 | +0.333 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | -0.667 | 0.333 | +1.000 |
| nemotron-3-super | 0.333 | -0.333 | -0.666 |
| qwen3.5-122b | -0.333 | 0.667 | +1.000 |
| qwen3.6-27b | 0.000 | 0.667 | +0.667 |
| qwen3.8-27b | -0.333 | 1.000 | +1.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | 0.000 | 0.600 | +0.600 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | -0.067 | 1.000 | +1.067 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.733 | -0.267 |
| nemotron-3-super | 0.333 | 0.733 | +0.400 |
| qwen3.5-122b | 0.200 | 1.000 | +0.800 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 1.000 | +0.200 |
| gemma-4-31b | 1.000 | 0.800 | -0.200 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 0.800 | -0.200 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | -0.800 | 0.800 | +1.600 |
| mimo-v2.6-flash | 0.800 | 0.800 | +0.000 |
| nemotron-3-super | -0.800 | 0.800 | +1.600 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | -0.800 | 0.800 | +1.600 |
| qwen3.8-27b | -0.800 | 0.800 | +1.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 0.000 | -0.400 |
| gemma-4-31b | -0.600 | 0.000 | +0.600 |
| glm-5.3-flash | -0.600 | 0.800 | +1.400 |
| gpt-oss-120b | -1.000 | 0.800 | +1.800 |
| kimi-k3 | -0.600 | 1.000 | +1.600 |
| mimo-v2.6-flash | 0.000 | -0.200 | -0.200 |
| nemotron-3-super | -0.200 | 0.000 | +0.200 |
| qwen3.5-122b | -0.400 | 1.000 | +1.400 |
| qwen3.6-27b | 0.600 | 0.000 | -0.600 |
| qwen3.8-27b | -0.600 | 0.000 | +0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | -1.000 | +0.000 |
| gemma-4-31b | -1.000 | -1.000 | +0.000 |
| glm-5.3-flash | 0.000 | -0.667 | -0.667 |
| gpt-oss-120b | -1.000 | -1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -0.667 | -1.000 | -0.333 |
| nemotron-3-super | -1.000 | 1.000 | +2.000 |
| qwen3.5-122b | -1.000 | -1.000 | +0.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 0.667 | +0.334 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | -0.667 | 0.667 | +1.334 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 1.000 | +0.667 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | -0.333 | 1.000 | +1.333 |
| kimi-k3 | -0.333 | 1.000 | +1.333 |
| mimo-v2.6-flash | 0.333 | 1.000 | +0.667 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 0.333 | 1.000 | +0.667 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 1.000 | +0.667 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.333 | 1.000 | +0.667 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 0.200 | 1.000 | +0.800 |
| glm-5.3-flash | 0.067 | 1.000 | +0.933 |
| gpt-oss-120b | 0.600 | 1.000 | +0.400 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.067 | 1.000 | +0.933 |
| mimo-v2.6-flash | 0.733 | 1.000 | +0.267 |
| nemotron-3-super | 0.467 | 1.000 | +0.533 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 0.067 | 1.000 | +0.933 |
| qwen3.8-27b | 0.067 | 1.000 | +0.933 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 1.000 | +1.000 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 0.333 | 1.000 | +0.667 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| kimi-k3 | 0.333 | 1.000 | +0.667 |
| mimo-v2.6-flash | 0.333 | 1.000 | +0.667 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 0.333 | 1.000 | +0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.733 | 1.000 | +0.267 |
| gemma-4-31b | 0.067 | 1.000 | +0.933 |
| glm-5.3-flash | -0.200 | 1.000 | +1.200 |
| gpt-oss-120b | 0.733 | 1.000 | +0.267 |
| gpt-oss-20b | 0.733 | 1.000 | +0.267 |
| kimi-k3 | 0.067 | 1.000 | +0.933 |
| mimo-v2.6-flash | -0.200 | 1.000 | +1.200 |
| nemotron-3-super | 0.733 | 1.000 | +0.267 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 0.733 | 1.000 | +0.267 |
| qwen3.8-27b | 0.067 | 1.000 | +0.933 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | -0.333 | +0.667 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | -1.000 | 0.667 | +1.667 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -0.333 | 1.000 | +1.333 |
| nemotron-3-super | 0.333 | 0.333 | +0.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.600 | 0.400 | +1.000 |
| gemma-4-31b | -0.400 | 0.400 | +0.800 |
| glm-5.3-flash | -0.200 | 0.400 | +0.600 |
| gpt-oss-120b | 0.200 | 0.400 | +0.200 |
| gpt-oss-20b | 0.000 | 0.400 | +0.400 |
| kimi-k3 | -0.200 | 0.400 | +0.600 |
| mimo-v2.6-flash | -0.200 | 0.400 | +0.600 |
| nemotron-3-super | 0.000 | 0.400 | +0.400 |
| qwen3.5-122b | 0.400 | 0.400 | +0.000 |
| qwen3.6-27b | 0.400 | 0.400 | +0.000 |
| qwen3.8-27b | -0.400 | 1.000 | +1.400 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 1.000 | +0.200 |
| gemma-4-31b | 0.800 | 1.000 | +0.200 |
| glm-5.3-flash | 0.800 | 1.000 | +0.200 |
| gpt-oss-120b | 0.800 | 1.000 | +0.200 |
| gpt-oss-20b | -0.400 | 1.000 | +1.400 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | -0.800 | 0.400 | +1.200 |
| nemotron-3-super | 0.600 | 1.000 | +0.400 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 0.800 | 1.000 | +0.200 |
| qwen3.8-27b | -0.600 | 1.000 | +1.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.800 | 0.200 | +1.000 |
| gemma-4-31b | -0.800 | 0.200 | +1.000 |
| glm-5.3-flash | 0.400 | 0.200 | -0.200 |
| gpt-oss-120b | -0.800 | 0.400 | +1.200 |
| gpt-oss-20b | -0.800 | -0.800 | +0.000 |
| kimi-k3 | -0.800 | 0.200 | +1.000 |
| mimo-v2.6-flash | -0.800 | -0.400 | +0.400 |
| nemotron-3-super | -0.800 | 0.200 | +1.000 |
| qwen3.5-122b | 0.400 | 0.200 | -0.200 |
| qwen3.6-27b | -0.800 | 0.200 | +1.000 |
| qwen3.8-27b | 0.400 | 0.200 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.400 | 0.400 | +0.800 |
| gemma-4-31b | -0.400 | 1.000 | +1.400 |
| glm-5.3-flash | 0.400 | 1.000 | +0.600 |
| gpt-oss-120b | 0.400 | 1.000 | +0.600 |
| gpt-oss-20b | 0.400 | 0.600 | +0.200 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -0.200 | 1.000 | +1.200 |
| nemotron-3-super | 0.600 | 1.000 | +0.400 |
| qwen3.5-122b | 0.200 | 1.000 | +0.800 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.429 | 0.810 | +0.381 |
| gemma-4-31b | 0.714 | 0.810 | +0.096 |
| glm-5.3-flash | 0.524 | 1.000 | +0.476 |
| gpt-oss-120b | 0.429 | 1.000 | +0.571 |
| gpt-oss-20b | -0.048 | 0.000 | +0.048 |
| kimi-k3 | 0.429 | 0.810 | +0.381 |
| mimo-v2.6-flash | 0.333 | 1.000 | +0.667 |
| nemotron-3-super | 0.143 | 0.810 | +0.667 |
| qwen3.5-122b | -0.429 | 0.524 | +0.953 |
| qwen3.6-27b | 0.429 | 0.810 | +0.381 |
| qwen3.8-27b | -0.143 | 1.000 | +1.143 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | -1.000 | 1.000 | +2.000 |
| mimo-v2.6-flash | -0.667 | 1.000 | +1.667 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | -1.000 | +0.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -0.333 | 1.000 | +1.333 |
| nemotron-3-super | 0.667 | 0.333 | -0.334 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 0.333 | +0.333 |
| gemma-4-31b | 0.333 | 0.333 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | -0.333 | 1.000 | +1.333 |
| kimi-k3 | 0.333 | 1.000 | +0.667 |
| mimo-v2.6-flash | 0.333 | 0.333 | +0.000 |
| nemotron-3-super | 0.000 | 0.000 | +0.000 |
| qwen3.5-122b | -0.333 | 1.000 | +1.333 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -0.333 | 1.000 | +1.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 1.000 | +0.400 |
| gemma-4-31b | 0.600 | 1.000 | +0.400 |
| glm-5.3-flash | 0.800 | 1.000 | +0.200 |
| gpt-oss-120b | 0.200 | 1.000 | +0.800 |
| gpt-oss-20b | 0.600 | 1.000 | +0.400 |
| kimi-k3 | 0.400 | 1.000 | +0.600 |
| mimo-v2.6-flash | 0.400 | 1.000 | +0.600 |
| nemotron-3-super | 0.600 | 0.800 | +0.200 |
| qwen3.5-122b | 0.400 | 1.000 | +0.600 |
| qwen3.6-27b | 0.400 | 1.000 | +0.600 |
| qwen3.8-27b | 0.400 | 1.000 | +0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.200 | -0.400 | -0.200 |
| gemma-4-31b | -0.200 | -0.200 | +0.000 |
| glm-5.3-flash | 0.200 | 1.000 | +0.800 |
| gpt-oss-120b | -0.400 | 0.200 | +0.600 |
| gpt-oss-20b | -0.400 | -0.400 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -0.200 | 0.200 | +0.400 |
| nemotron-3-super | -0.200 | 1.000 | +1.200 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | -0.400 | 1.000 | +1.400 |
| qwen3.8-27b | -0.200 | 1.000 | +1.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 0.200 | +0.200 |
| gemma-4-31b | 0.400 | 1.000 | +0.600 |
| glm-5.3-flash | 0.400 | 0.800 | +0.400 |
| gpt-oss-120b | 0.400 | 1.000 | +0.600 |
| kimi-k3 | 0.400 | 1.000 | +0.600 |
| mimo-v2.6-flash | 0.400 | 0.000 | -0.400 |
| nemotron-3-super | 0.400 | 1.000 | +0.600 |
| qwen3.5-122b | 0.400 | 1.000 | +0.600 |
| qwen3.6-27b | 0.400 | 1.000 | +0.600 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 1.000 | +0.600 |
| gemma-4-31b | -0.400 | -0.200 | +0.200 |
| glm-5.3-flash | 0.200 | 1.000 | +0.800 |
| gpt-oss-120b | -0.400 | -0.400 | +0.000 |
| kimi-k3 | -0.400 | 1.000 | +1.400 |
| mimo-v2.6-flash | 0.400 | 0.200 | -0.200 |
| nemotron-3-super | 0.800 | 0.000 | -0.800 |
| qwen3.5-122b | 0.400 | 0.200 | -0.200 |
| qwen3.6-27b | -0.400 | 1.000 | +1.400 |
| qwen3.8-27b | -0.400 | 1.000 | +1.400 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.333 | 1.000 | +0.667 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | -0.333 | 0.333 | +0.666 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -0.667 | 1.000 | +1.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.600 | +0.000 |
| gemma-4-31b | 0.600 | 1.000 | +0.400 |
| glm-5.3-flash | -0.800 | 1.000 | +1.800 |
| gpt-oss-120b | 0.600 | 0.400 | -0.200 |
| gpt-oss-20b | 0.000 | 0.400 | +0.400 |
| kimi-k3 | -0.800 | 0.400 | +1.200 |
| mimo-v2.6-flash | -0.600 | 0.800 | +1.400 |
| nemotron-3-super | 0.600 | 0.600 | +0.000 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | 0.600 | 1.000 | +0.400 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 0.667 | +0.334 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 0.333 | 1.000 | +0.667 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | 0.333 | 0.000 | -0.333 |
| kimi-k3 | 0.333 | 1.000 | +0.667 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | 0.333 | -0.333 | -0.666 |
| qwen3.5-122b | 0.333 | 1.000 | +0.667 |
| qwen3.6-27b | 0.333 | 1.000 | +0.667 |
| qwen3.8-27b | 0.333 | 1.000 | +0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | -1.000 | +0.000 |
| gemma-4-31b | -1.000 | 1.000 | +2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -0.667 | -0.667 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.800 | 1.000 | +0.200 |
| gpt-oss-120b | 0.800 | 1.000 | +0.200 |
| gpt-oss-20b | 0.800 | 1.000 | +0.200 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -0.600 | 0.800 | +1.400 |
| nemotron-3-super | 0.200 | 1.000 | +0.800 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | -1.000 | 1.000 | +2.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | -1.000 | 1.000 | +2.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.333 | 1.000 | +0.667 |
| mimo-v2.6-flash | 0.667 | 1.000 | +0.333 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.667 | 1.000 | +0.333 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 0.400 | +0.000 |
| gemma-4-31b | 0.800 | 0.800 | +0.000 |
| glm-5.3-flash | 0.400 | 0.800 | +0.400 |
| gpt-oss-120b | 0.400 | 1.000 | +0.600 |
| gpt-oss-20b | 0.400 | 1.000 | +0.600 |
| kimi-k3 | 0.400 | 1.000 | +0.600 |
| mimo-v2.6-flash | 0.800 | 0.400 | -0.400 |
| nemotron-3-super | -0.200 | 1.000 | +1.200 |
| qwen3.5-122b | 0.400 | 1.000 | +0.600 |
| qwen3.6-27b | 0.400 | 1.000 | +0.600 |
| qwen3.8-27b | 0.400 | 1.000 | +0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 0.667 | -0.333 |
| glm-5.3-flash | -0.667 | 1.000 | +1.667 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | -0.667 | 1.000 | +1.667 |
| mimo-v2.6-flash | 1.000 | 0.667 | -0.333 |
| nemotron-3-super | 0.000 | 1.000 | +1.000 |
| qwen3.5-122b | -0.667 | 0.667 | +1.334 |
| qwen3.6-27b | 1.000 | 0.667 | -0.333 |
| qwen3.8-27b | 1.000 | 0.667 | -0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.667 | +0.000 |
| gemma-4-31b | 0.667 | 0.667 | +0.000 |
| glm-5.3-flash | 0.000 | 0.667 | +0.667 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.333 | 0.667 | +0.334 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 0.667 | 0.667 | +0.000 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.333 | 1.000 | +0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 0.200 | +0.200 |
| gemma-4-31b | 0.000 | 0.200 | +0.200 |
| glm-5.3-flash | 0.000 | 0.800 | +0.800 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 0.200 | 0.200 | +0.000 |
| mimo-v2.6-flash | 0.000 | 0.000 | +0.000 |
| nemotron-3-super | 0.200 | 0.800 | +0.600 |
| qwen3.5-122b | 0.000 | 0.200 | +0.200 |
| qwen3.6-27b | 0.000 | 0.200 | +0.200 |
| qwen3.8-27b | 0.000 | 0.800 | +0.800 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 1.000 | +0.600 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.800 | 1.000 | +0.200 |
| gpt-oss-120b | 0.400 | 1.000 | +0.600 |
| gpt-oss-20b | -0.200 | 1.000 | +1.200 |
| kimi-k3 | 0.400 | 1.000 | +0.600 |
| mimo-v2.6-flash | 0.400 | 1.000 | +0.600 |
| nemotron-3-super | 0.600 | 1.000 | +0.400 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 0.000 | +0.333 |
| gemma-4-31b | -1.000 | 0.000 | +1.000 |
| glm-5.3-flash | 0.000 | 0.000 | +0.000 |
| gpt-oss-120b | 0.000 | 0.000 | +0.000 |
| gpt-oss-20b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | -1.000 | 0.000 | +1.000 |
| mimo-v2.6-flash | -0.333 | 0.000 | +0.333 |
| nemotron-3-super | 0.000 | 0.000 | +0.000 |
| qwen3.5-122b | -0.333 | 0.000 | +0.333 |
| qwen3.6-27b | 0.000 | 0.000 | +0.000 |
| qwen3.8-27b | -1.000 | 0.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | -1.000 | 1.000 | +2.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | -0.333 | -0.333 |
| gemma-4-31b | -0.333 | -0.333 | +0.000 |
| glm-5.3-flash | -0.667 | 0.000 | +0.667 |
| gpt-oss-120b | -0.333 | -0.333 | +0.000 |
| gpt-oss-20b | -0.333 | 0.000 | +0.333 |
| kimi-k3 | -0.333 | 0.333 | +0.666 |
| mimo-v2.6-flash | -0.333 | -0.333 | +0.000 |
| nemotron-3-super | -0.667 | -0.333 | +0.334 |
| qwen3.5-122b | -0.667 | 0.333 | +1.000 |
| qwen3.6-27b | -0.333 | 0.333 | +0.666 |
| qwen3.8-27b | -0.333 | 0.333 | +0.666 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | 0.667 | 1.000 | +0.333 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.333 | 1.000 | +0.667 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | 0.667 | 0.000 | -0.667 |
| kimi-k3 | 0.333 | 1.000 | +0.667 |
| mimo-v2.6-flash | 0.667 | 1.000 | +0.333 |
| nemotron-3-super | 0.333 | 1.000 | +0.667 |
| qwen3.5-122b | 0.333 | 1.000 | +0.667 |
| qwen3.6-27b | 0.667 | 0.000 | -0.667 |
| qwen3.8-27b | 0.333 | 1.000 | +0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.667 | +0.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | 0.667 | 1.000 | +0.333 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -0.333 | 1.000 | +1.333 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | 0.667 | 1.000 | +0.333 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.667 | 1.000 | +0.333 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 1.000 | 0.000 | -1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | -0.333 | 1.000 | +1.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | -1.000 | 1.000 | +2.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 1.000 | +0.400 |
| gemma-4-31b | 0.600 | 1.000 | +0.400 |
| glm-5.3-flash | 0.800 | 1.000 | +0.200 |
| gpt-oss-120b | 0.200 | 1.000 | +0.800 |
| gpt-oss-20b | 0.800 | 1.000 | +0.200 |
| kimi-k3 | 0.600 | 1.000 | +0.400 |
| mimo-v2.6-flash | 0.800 | 1.000 | +0.200 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 0.600 | 1.000 | +0.400 |
| qwen3.8-27b | 0.800 | 1.000 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | -0.600 | -0.600 |
| gemma-4-31b | -0.600 | 0.600 | +1.200 |
| glm-5.3-flash | 0.800 | 0.800 | +0.000 |
| gpt-oss-120b | 0.000 | 0.800 | +0.800 |
| kimi-k3 | 0.000 | 0.800 | +0.800 |
| mimo-v2.6-flash | -0.600 | 0.000 | +0.600 |
| nemotron-3-super | 0.800 | 0.800 | +0.000 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 0.000 | 0.200 | +0.200 |
| qwen3.8-27b | 0.800 | 0.800 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.333 | -0.267 |
| gemma-4-31b | 0.333 | 0.733 | +0.400 |
| glm-5.3-flash | 0.600 | 1.000 | +0.400 |
| gpt-oss-120b | 0.600 | 0.733 | +0.133 |
| gpt-oss-20b | 0.733 | 0.333 | -0.400 |
| kimi-k3 | 0.333 | 0.733 | +0.400 |
| mimo-v2.6-flash | 0.333 | 0.600 | +0.267 |
| nemotron-3-super | 0.333 | 1.000 | +0.667 |
| qwen3.5-122b | 0.333 | 1.000 | +0.667 |
| qwen3.6-27b | 0.600 | 1.000 | +0.400 |
| qwen3.8-27b | 0.067 | 0.733 | +0.666 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | -1.000 | +0.000 |
| gemma-4-31b | -1.000 | -1.000 | +0.000 |
| glm-5.3-flash | -1.000 | -1.000 | +0.000 |
| gpt-oss-120b | -1.000 | -1.000 | +0.000 |
| gpt-oss-20b | -1.000 | 0.000 | +1.000 |
| kimi-k3 | -1.000 | -1.000 | +0.000 |
| mimo-v2.6-flash | -1.000 | -1.000 | +0.000 |
| nemotron-3-super | -1.000 | -1.000 | +0.000 |
| qwen3.5-122b | -1.000 | -0.600 | +0.400 |
| qwen3.6-27b | -1.000 | -1.000 | +0.000 |
| qwen3.8-27b | -1.000 | 0.800 | +1.800 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 0.400 | +0.000 |
| gemma-4-31b | 0.400 | 0.800 | +0.400 |
| glm-5.3-flash | -0.200 | 0.200 | +0.400 |
| gpt-oss-120b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | -0.400 | 1.000 | +1.400 |
| mimo-v2.6-flash | 0.400 | 0.800 | +0.400 |
| nemotron-3-super | 0.400 | 1.000 | +0.600 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 0.200 | -0.200 | -0.400 |
| qwen3.8-27b | 0.000 | -0.200 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.800 | -0.200 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.667 | +0.000 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.667 | 0.667 | +0.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | -0.667 | 1.000 | +1.667 |
| gpt-oss-120b | 1.000 | 0.000 | -1.000 |
| gpt-oss-20b | 0.333 | 1.000 | +0.667 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.667 | -0.333 |
| nemotron-3-super | -0.667 | 1.000 | +1.667 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.905 | 0.905 | +0.000 |
| gemma-4-31b | 0.905 | 1.000 | +0.095 |
| glm-5.3-flash | 0.905 | 1.000 | +0.095 |
| gpt-oss-120b | 0.905 | 1.000 | +0.095 |
| gpt-oss-20b | -0.714 | 0.905 | +1.619 |
| kimi-k3 | 0.905 | 1.000 | +0.095 |
| mimo-v2.6-flash | 0.905 | 1.000 | +0.095 |
| nemotron-3-super | 0.905 | 1.000 | +0.095 |
| qwen3.5-122b | 0.905 | 1.000 | +0.095 |
| qwen3.6-27b | 0.714 | 1.000 | +0.286 |
| qwen3.8-27b | 0.905 | 1.000 | +0.095 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.667 | -0.333 | +0.334 |
| gemma-4-31b | -1.000 | -0.333 | +0.667 |
| glm-5.3-flash | -0.333 | 0.000 | +0.333 |
| gpt-oss-120b | -1.000 | -0.333 | +0.667 |
| gpt-oss-20b | -0.333 | 0.000 | +0.333 |
| kimi-k3 | -0.667 | 0.000 | +0.667 |
| mimo-v2.6-flash | -0.333 | -0.667 | -0.334 |
| nemotron-3-super | -0.667 | -0.667 | +0.000 |
| qwen3.5-122b | -0.333 | -0.333 | +0.000 |
| qwen3.6-27b | -0.333 | -0.333 | +0.000 |
| qwen3.8-27b | -0.333 | -0.333 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 0.000 | +0.000 |
| gemma-4-31b | 0.200 | 0.000 | -0.200 |
| glm-5.3-flash | 0.000 | 1.000 | +1.000 |
| gpt-oss-120b | 0.400 | 1.000 | +0.600 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.000 | 0.000 | +0.000 |
| nemotron-3-super | 0.000 | 0.400 | +0.400 |
| qwen3.5-122b | 0.400 | 0.400 | +0.000 |
| qwen3.6-27b | 0.400 | 1.000 | +0.600 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.400 | -0.200 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | 0.600 | 0.400 | -0.200 |
| gpt-oss-120b | -0.200 | 0.400 | +0.600 |
| gpt-oss-20b | 0.000 | 0.400 | +0.400 |
| kimi-k3 | -0.600 | 0.400 | +1.000 |
| mimo-v2.6-flash | -0.800 | 0.400 | +1.200 |
| nemotron-3-super | 0.600 | 0.400 | -0.200 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | -0.200 | 0.400 | +0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.333 | 1.000 | +0.667 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.000 | 1.000 | +1.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 0.667 | -0.333 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.667 | 1.000 | +0.333 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 1.000 | +0.200 |
| gemma-4-31b | -0.800 | 1.000 | +1.800 |
| glm-5.3-flash | 0.800 | 0.800 | +0.000 |
| gpt-oss-120b | -0.800 | 0.000 | +0.800 |
| gpt-oss-20b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | 0.800 | 0.200 | -0.600 |
| mimo-v2.6-flash | -0.800 | 0.000 | +0.800 |
| nemotron-3-super | 0.800 | 0.200 | -0.600 |
| qwen3.5-122b | 0.800 | 0.200 | -0.600 |
| qwen3.6-27b | -0.800 | 0.200 | +1.000 |
| qwen3.8-27b | 0.800 | 0.200 | -0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| gpt-oss-20b | -0.333 | 0.000 | +0.333 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 0.667 | 0.667 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.000 | -0.667 |
| gemma-4-31b | 0.000 | -0.333 | -0.333 |
| glm-5.3-flash | -0.333 | 1.000 | +1.333 |
| gpt-oss-120b | 0.667 | 0.333 | -0.334 |
| gpt-oss-20b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | 0.000 | 1.000 | +1.000 |
| mimo-v2.6-flash | 0.333 | 0.000 | -0.333 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 0.000 | 1.000 | +1.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.667 | 0.000 | -0.667 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 0.667 | 0.000 | -0.667 |
| gpt-oss-20b | 0.667 | 0.000 | -0.667 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.667 | 0.000 | -0.667 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | -0.667 | 0.000 | +0.667 |
| qwen3.6-27b | -0.667 | 0.000 | +0.667 |
| qwen3.8-27b | -1.000 | 0.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.619 | 0.238 | -0.381 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.429 | 1.000 | +0.571 |
| gpt-oss-20b | 1.000 | 0.333 | -0.667 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.048 | 1.000 | +0.952 |
| nemotron-3-super | 0.238 | 1.000 | +0.762 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.200 | 0.400 | +0.200 |
| gemma-4-31b | 0.200 | 0.400 | +0.200 |
| glm-5.3-flash | 0.200 | 0.400 | +0.200 |
| gpt-oss-120b | 0.200 | 0.400 | +0.200 |
| gpt-oss-20b | 0.200 | 0.400 | +0.200 |
| kimi-k3 | 0.200 | 0.400 | +0.200 |
| mimo-v2.6-flash | 0.600 | 0.400 | -0.200 |
| nemotron-3-super | 0.200 | 0.400 | +0.200 |
| qwen3.5-122b | 0.200 | 0.400 | +0.200 |
| qwen3.6-27b | 0.200 | 0.400 | +0.200 |
| qwen3.8-27b | 0.200 | 0.400 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 1.000 | +0.200 |
| gemma-4-31b | 0.800 | 1.000 | +0.200 |
| glm-5.3-flash | 0.800 | 0.800 | +0.000 |
| gpt-oss-120b | 0.800 | 1.000 | +0.200 |
| gpt-oss-20b | 0.800 | 0.800 | +0.000 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | 0.600 | 0.800 | +0.200 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 0.800 | 1.000 | +0.200 |
| qwen3.8-27b | 0.800 | 1.000 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 0.800 | +0.000 |
| gemma-4-31b | 0.800 | 0.800 | +0.000 |
| glm-5.3-flash | 0.200 | 1.000 | +0.800 |
| gpt-oss-120b | 1.000 | 0.600 | -0.400 |
| gpt-oss-20b | 0.000 | 0.400 | +0.400 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | 1.000 | 0.400 | -0.600 |
| nemotron-3-super | -0.200 | 0.800 | +1.000 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 0.800 | 1.000 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 0.333 | +0.000 |
| gemma-4-31b | 0.333 | 1.000 | +0.667 |
| glm-5.3-flash | 0.333 | 1.000 | +0.667 |
| gpt-oss-120b | 0.000 | 1.000 | +1.000 |
| gpt-oss-20b | 0.333 | 0.000 | -0.333 |
| kimi-k3 | -0.667 | 0.000 | +0.667 |
| mimo-v2.6-flash | 0.333 | 0.667 | +0.334 |
| nemotron-3-super | 0.000 | -0.333 | -0.333 |
| qwen3.5-122b | 0.333 | 0.000 | -0.333 |
| qwen3.6-27b | 0.333 | 0.000 | -0.333 |
| qwen3.8-27b | 0.333 | 0.000 | -0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | -0.667 | 1.000 | +1.667 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.667 | 1.000 | +0.333 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 0.200 | 0.800 | +0.600 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.800 | 1.000 | +0.200 |
| gpt-oss-20b | 0.800 | 0.800 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.600 | 1.000 | +0.400 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.333 | 1.000 | +0.667 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.333 | 0.667 | +0.334 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.667 | +0.000 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | -0.667 | -1.000 | -0.333 |
| gpt-oss-20b | -0.667 | -0.667 | +0.000 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.667 | 0.667 | +0.000 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | 0.667 | 0.667 | +0.000 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.667 | 0.667 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 1.000 | +0.333 |
| gemma-4-31b | 0.667 | 0.667 | +0.000 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | 0.667 | 0.333 | -0.334 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.667 | 0.333 | -0.334 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.000 | 0.000 | +0.000 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 1.000 | +0.200 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.400 | 1.000 | +0.600 |
| nemotron-3-super | 0.600 | 1.000 | +0.400 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.600 | +0.000 |
| gemma-4-31b | 0.600 | 0.600 | +0.000 |
| glm-5.3-flash | 0.600 | 0.600 | +0.000 |
| gpt-oss-120b | 0.600 | 0.600 | +0.000 |
| gpt-oss-20b | 0.000 | 0.600 | +0.600 |
| kimi-k3 | 0.600 | 0.600 | +0.000 |
| mimo-v2.6-flash | 0.600 | 1.000 | +0.400 |
| nemotron-3-super | 0.400 | 0.600 | +0.200 |
| qwen3.5-122b | 0.600 | 0.600 | +0.000 |
| qwen3.6-27b | 0.600 | 0.600 | +0.000 |
| qwen3.8-27b | 0.600 | 0.600 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.467 | -0.067 | +0.400 |
| gemma-4-31b | -0.600 | -0.067 | +0.533 |
| glm-5.3-flash | -0.467 | -0.467 | +0.000 |
| gpt-oss-120b | -0.600 | -0.467 | +0.133 |
| kimi-k3 | -0.600 | -0.467 | +0.133 |
| mimo-v2.6-flash | -0.333 | -0.333 | +0.000 |
| nemotron-3-super | -0.467 | 0.067 | +0.534 |
| qwen3.5-122b | -0.467 | -0.733 | -0.266 |
| qwen3.6-27b | -0.200 | -0.467 | -0.267 |
| qwen3.8-27b | -0.467 | -0.733 | -0.266 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.667 | +0.000 |
| gemma-4-31b | 0.667 | 0.667 | +0.000 |
| glm-5.3-flash | 0.667 | 0.667 | +0.000 |
| gpt-oss-120b | 0.000 | 0.667 | +0.667 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | 0.000 | 0.667 | +0.667 |
| mimo-v2.6-flash | 0.667 | -0.333 | -1.000 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | 0.000 | 0.667 | +0.667 |
| qwen3.6-27b | 0.667 | 0.667 | +0.000 |
| qwen3.8-27b | 0.667 | 0.667 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.667 | -0.333 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.667 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.667 | 0.000 | -0.667 |
| gpt-oss-120b | 0.667 | 0.667 | +0.000 |
| gpt-oss-20b | 0.000 | 0.667 | +0.667 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.333 | 1.000 | +0.667 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | 0.667 | 0.667 | +0.000 |
| qwen3.6-27b | 1.000 | 0.667 | -0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.400 | 0.400 | +0.000 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | 0.200 | 0.400 | +0.200 |
| gpt-oss-120b | 0.200 | 0.400 | +0.200 |
| gpt-oss-20b | 0.600 | 0.400 | -0.200 |
| kimi-k3 | 0.200 | 0.400 | +0.200 |
| mimo-v2.6-flash | 0.000 | 0.400 | +0.400 |
| nemotron-3-super | 0.600 | 0.400 | -0.200 |
| qwen3.5-122b | 0.200 | 0.400 | +0.200 |
| qwen3.6-27b | 0.200 | 0.400 | +0.200 |
| qwen3.8-27b | 0.200 | 0.400 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 0.333 | +0.000 |
| gemma-4-31b | 0.333 | 0.333 | +0.000 |
| glm-5.3-flash | 0.333 | 0.333 | +0.000 |
| gpt-oss-120b | 0.333 | 0.333 | +0.000 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | 0.333 | 0.333 | +0.000 |
| mimo-v2.6-flash | 0.333 | 0.333 | +0.000 |
| nemotron-3-super | 0.333 | 0.333 | +0.000 |
| qwen3.5-122b | 0.333 | 0.333 | +0.000 |
| qwen3.6-27b | -0.667 | 0.333 | +1.000 |
| qwen3.8-27b | 0.333 | 0.333 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.000 | 0.333 | +0.333 |
| nemotron-3-super | 1.000 | 0.000 | -1.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 0.333 | 1.000 | +0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 1.000 | +0.200 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.200 | 1.000 | +0.800 |
| gpt-oss-120b | 0.200 | 1.000 | +0.800 |
| gpt-oss-20b | 1.000 | 0.200 | -0.800 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.600 | -0.400 |
| nemotron-3-super | 0.600 | 1.000 | +0.400 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.667 | +0.000 |
| gemma-4-31b | 0.667 | 1.000 | +0.333 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 0.667 | -0.333 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 0.667 | 1.000 | +0.333 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 0.000 | 1.000 | +1.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | 0.333 | 1.000 | +0.667 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | 0.000 | 1.000 | +1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.667 | 0.667 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 0.667 | -0.333 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 1.000 | +0.200 |
| gemma-4-31b | 0.800 | 1.000 | +0.200 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | 0.800 | 0.200 | -0.600 |
| nemotron-3-super | 0.200 | 0.800 | +0.600 |
| qwen3.5-122b | 1.000 | 0.800 | -0.200 |
| qwen3.6-27b | 0.800 | 1.000 | +0.200 |
| qwen3.8-27b | 0.800 | 1.000 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 1.000 | +0.200 |
| gemma-4-31b | 0.800 | 1.000 | +0.200 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.800 | 0.000 | -0.800 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | 0.800 | 1.000 | +0.200 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 0.800 | 1.000 | +0.200 |
| qwen3.8-27b | 0.800 | 1.000 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.600 | +0.000 |
| gemma-4-31b | 0.600 | 0.600 | +0.000 |
| glm-5.3-flash | 0.600 | 0.600 | +0.000 |
| gpt-oss-120b | 0.600 | 0.600 | +0.000 |
| gpt-oss-20b | -0.600 | 0.600 | +1.200 |
| kimi-k3 | 0.600 | 0.600 | +0.000 |
| mimo-v2.6-flash | 0.600 | 0.600 | +0.000 |
| nemotron-3-super | 0.600 | 0.600 | +0.000 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.600 | +0.000 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.333 | 1.000 | +0.667 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 0.667 | -0.333 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 0.667 | 0.667 | +0.000 |
| gpt-oss-20b | 0.000 | 0.667 | +0.667 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.400 | -0.400 | +0.000 |
| gemma-4-31b | -0.200 | -0.400 | -0.200 |
| glm-5.3-flash | -0.400 | -0.800 | -0.400 |
| gpt-oss-120b | -0.400 | -0.400 | +0.000 |
| kimi-k3 | -0.400 | -0.400 | +0.000 |
| mimo-v2.6-flash | -0.200 | -0.400 | -0.200 |
| nemotron-3-super | -0.400 | 0.600 | +1.000 |
| qwen3.5-122b | -0.200 | -0.600 | -0.400 |
| qwen3.6-27b | -0.400 | 1.000 | +1.400 |
| qwen3.8-27b | 0.000 | -0.600 | -0.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.200 | 0.800 | +1.000 |
| gemma-4-31b | -0.200 | 0.400 | +0.600 |
| glm-5.3-flash | -0.200 | -1.000 | -0.800 |
| gpt-oss-120b | -0.200 | 0.400 | +0.600 |
| gpt-oss-20b | -0.600 | -0.600 | +0.000 |
| kimi-k3 | 0.400 | -1.000 | -1.400 |
| mimo-v2.6-flash | -0.200 | -0.800 | -0.600 |
| nemotron-3-super | 0.000 | -1.000 | -1.000 |
| qwen3.5-122b | -0.200 | 1.000 | +1.200 |
| qwen3.6-27b | -0.400 | -1.000 | -0.600 |
| qwen3.8-27b | -0.600 | 1.000 | +1.600 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.600 | +0.000 |
| gemma-4-31b | 0.600 | 0.600 | +0.000 |
| glm-5.3-flash | 0.600 | 0.600 | +0.000 |
| gpt-oss-120b | -0.600 | 0.400 | +1.000 |
| gpt-oss-20b | 0.600 | 0.400 | -0.200 |
| kimi-k3 | 0.600 | 0.600 | +0.000 |
| mimo-v2.6-flash | 0.600 | 0.600 | +0.000 |
| nemotron-3-super | 0.600 | 0.600 | +0.000 |
| qwen3.5-122b | 0.600 | 0.600 | +0.000 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | 0.600 | 0.600 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.600 | 1.000 | +0.400 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.867 | 0.600 | -0.267 |
| gemma-4-31b | 0.733 | 1.000 | +0.267 |
| glm-5.3-flash | 0.867 | 1.000 | +0.133 |
| gpt-oss-120b | 0.867 | 0.600 | -0.267 |
| gpt-oss-20b | 0.867 | 1.000 | +0.133 |
| kimi-k3 | 0.867 | 1.000 | +0.133 |
| mimo-v2.6-flash | 0.867 | 1.000 | +0.133 |
| nemotron-3-super | 0.867 | 0.600 | -0.267 |
| qwen3.5-122b | 0.867 | 1.000 | +0.133 |
| qwen3.6-27b | 0.867 | 1.000 | +0.133 |
| qwen3.8-27b | 0.867 | 1.000 | +0.133 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 0.667 | -0.333 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 1.000 | 0.667 | -0.333 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.667 | 1.000 | +0.333 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 0.667 | 1.000 | +0.333 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 0.667 | +0.667 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 0.667 | -0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 0.667 | +0.667 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.333 | 0.000 | -0.333 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 0.000 | -1.000 |
| gpt-oss-120b | 0.000 | 0.000 | +0.000 |
| gpt-oss-20b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.333 | 1.000 | +0.667 |
| qwen3.5-122b | 1.000 | 0.667 | -0.333 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 0.000 | 1.000 | +1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.667 | +0.000 |
| gemma-4-31b | 0.667 | 0.667 | +0.000 |
| glm-5.3-flash | 0.667 | 0.667 | +0.000 |
| gpt-oss-120b | 0.667 | 0.667 | +0.000 |
| gpt-oss-20b | 0.000 | 0.333 | +0.333 |
| kimi-k3 | 0.667 | 0.667 | +0.000 |
| mimo-v2.6-flash | 0.667 | 0.667 | +0.000 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | 0.667 | 0.667 | +0.000 |
| qwen3.6-27b | 0.667 | 0.667 | +0.000 |
| qwen3.8-27b | 0.667 | 0.667 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 0.800 | +0.000 |
| gemma-4-31b | 0.800 | 0.800 | +0.000 |
| glm-5.3-flash | 0.800 | 0.600 | -0.200 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.800 | 1.000 | +0.200 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | 1.000 | 0.800 | -0.200 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 0.800 | 0.800 | +0.000 |
| qwen3.6-27b | 0.800 | 0.800 | +0.000 |
| qwen3.8-27b | 0.800 | 0.800 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | -0.200 | -1.200 |
| gpt-oss-20b | 0.200 | 0.000 | -0.200 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 0.600 | -0.400 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.800 | -1.000 | -0.200 |
| gemma-4-31b | 0.800 | 1.000 | +0.200 |
| glm-5.3-flash | -0.600 | 1.000 | +1.600 |
| gpt-oss-120b | -0.800 | -0.400 | +0.400 |
| gpt-oss-20b | 0.000 | -0.400 | -0.400 |
| kimi-k3 | -1.000 | 0.800 | +1.800 |
| mimo-v2.6-flash | 0.800 | 0.200 | -0.600 |
| nemotron-3-super | 0.800 | -0.600 | -1.400 |
| qwen3.5-122b | -0.800 | -1.000 | -0.200 |
| qwen3.6-27b | 0.800 | -0.400 | -1.200 |
| qwen3.8-27b | 0.800 | 1.000 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.905 | 1.000 | +0.095 |
| gemma-4-31b | 0.905 | 1.000 | +0.095 |
| glm-5.3-flash | 0.905 | 1.000 | +0.095 |
| gpt-oss-120b | 0.905 | 1.000 | +0.095 |
| gpt-oss-20b | 0.905 | 0.000 | -0.905 |
| kimi-k3 | 0.905 | 1.000 | +0.095 |
| mimo-v2.6-flash | 0.905 | 1.000 | +0.095 |
| nemotron-3-super | 0.905 | 1.000 | +0.095 |
| qwen3.5-122b | 0.905 | 1.000 | +0.095 |
| qwen3.6-27b | 0.905 | 1.000 | +0.095 |
| qwen3.8-27b | 0.905 | 1.000 | +0.095 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.600 | +0.000 |
| gemma-4-31b | 0.600 | 0.600 | +0.000 |
| glm-5.3-flash | 0.600 | 0.600 | +0.000 |
| gpt-oss-120b | 0.600 | 0.400 | -0.200 |
| gpt-oss-20b | 0.000 | 0.600 | +0.600 |
| kimi-k3 | 0.600 | 0.400 | -0.200 |
| mimo-v2.6-flash | 0.600 | 0.600 | +0.000 |
| nemotron-3-super | 0.600 | 0.600 | +0.000 |
| qwen3.5-122b | 0.600 | 0.600 | +0.000 |
| qwen3.6-27b | 0.600 | 0.600 | +0.000 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.400 | -0.200 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | -0.800 | 0.400 | +1.200 |
| gpt-oss-120b | 0.600 | 0.400 | -0.200 |
| gpt-oss-20b | 0.600 | 0.000 | -0.600 |
| kimi-k3 | -0.600 | 0.400 | +1.000 |
| mimo-v2.6-flash | 0.600 | 0.400 | -0.200 |
| nemotron-3-super | 0.600 | 0.400 | -0.200 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 0.667 | -0.333 |
| glm-5.3-flash | -0.667 | 1.000 | +1.667 |
| gpt-oss-120b | 0.667 | 0.333 | -0.334 |
| gpt-oss-20b | -0.333 | 0.000 | +0.333 |
| kimi-k3 | 1.000 | 0.667 | -0.333 |
| mimo-v2.6-flash | 1.000 | 0.667 | -0.333 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 0.667 | -0.333 |
| qwen3.6-27b | 1.000 | 0.667 | -0.333 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.333 | 0.000 | -0.333 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.667 | -0.333 |
| nemotron-3-super | 0.000 | 0.333 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 0.000 | +0.333 |
| gemma-4-31b | 0.000 | 0.000 | +0.000 |
| glm-5.3-flash | 0.000 | 0.000 | +0.000 |
| gpt-oss-120b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | 0.000 | 0.000 | +0.000 |
| mimo-v2.6-flash | 0.000 | 0.000 | +0.000 |
| nemotron-3-super | -0.333 | 0.000 | +0.333 |
| qwen3.5-122b | 0.000 | 0.000 | +0.000 |
| qwen3.6-27b | 0.333 | 0.000 | -0.333 |
| qwen3.8-27b | 0.333 | 0.000 | -0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | -0.333 | -0.333 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.810 | 0.619 | -0.191 |
| nemotron-3-super | 0.524 | 0.619 | +0.095 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.800 | -0.200 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.400 | -0.200 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | 0.600 | 0.400 | -0.200 |
| gpt-oss-120b | 0.600 | 0.400 | -0.200 |
| gpt-oss-20b | 0.000 | 0.400 | +0.400 |
| kimi-k3 | 0.600 | 0.400 | -0.200 |
| mimo-v2.6-flash | -0.800 | 0.400 | +1.200 |
| nemotron-3-super | 0.600 | 0.400 | -0.200 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.667 | -0.333 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.333 | -0.667 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 0.667 | -0.333 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.800 | 0.000 | -0.800 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.600 | 1.000 | +0.400 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 0.067 | -0.266 |
| gemma-4-31b | 0.333 | 0.067 | -0.266 |
| glm-5.3-flash | 0.333 | 0.067 | -0.266 |
| gpt-oss-120b | -0.200 | 0.067 | +0.267 |
| gpt-oss-20b | -0.067 | 0.067 | +0.134 |
| kimi-k3 | -0.333 | 0.067 | +0.400 |
| mimo-v2.6-flash | 0.467 | 0.067 | -0.400 |
| nemotron-3-super | 0.333 | 0.067 | -0.266 |
| qwen3.5-122b | 0.333 | 0.067 | -0.266 |
| qwen3.6-27b | -0.333 | 0.067 | +0.400 |
| qwen3.8-27b | -0.067 | 0.067 | +0.134 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 0.000 | -0.800 |
| gemma-4-31b | 0.800 | 0.000 | -0.800 |
| glm-5.3-flash | 0.800 | 1.000 | +0.200 |
| gpt-oss-120b | 0.800 | 1.000 | +0.200 |
| gpt-oss-20b | 0.600 | 0.000 | -0.600 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | 0.800 | 1.000 | +0.200 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 0.800 | 1.000 | +0.200 |
| qwen3.6-27b | 0.800 | 1.000 | +0.200 |
| qwen3.8-27b | 0.800 | 1.000 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 0.800 | +0.000 |
| gemma-4-31b | 0.800 | 0.800 | +0.000 |
| glm-5.3-flash | 0.800 | 0.800 | +0.000 |
| gpt-oss-120b | 0.800 | 0.800 | +0.000 |
| gpt-oss-20b | 0.600 | 0.000 | -0.600 |
| kimi-k3 | 0.800 | 0.800 | +0.000 |
| mimo-v2.6-flash | 0.800 | 0.800 | +0.000 |
| nemotron-3-super | 0.800 | 0.800 | +0.000 |
| qwen3.5-122b | 0.800 | 0.800 | +0.000 |
| qwen3.6-27b | 0.800 | 0.800 | +0.000 |
| qwen3.8-27b | 0.800 | 0.800 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | -0.333 | -0.333 |
| gemma-4-31b | -0.333 | -0.333 | +0.000 |
| glm-5.3-flash | -0.333 | -0.333 | +0.000 |
| gpt-oss-120b | 0.000 | -0.333 | -0.333 |
| kimi-k3 | 0.000 | 0.000 | +0.000 |
| mimo-v2.6-flash | -0.333 | -0.333 | +0.000 |
| nemotron-3-super | -0.333 | -0.333 | +0.000 |
| qwen3.5-122b | 0.000 | 0.000 | +0.000 |
| qwen3.6-27b | 0.000 | 0.000 | +0.000 |
| qwen3.8-27b | 0.000 | 0.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 0.800 | -0.200 |
| gpt-oss-20b | 1.000 | 1.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 0.600 | -0.400 |
| qwen3.5-122b | 1.000 | 0.800 | -0.200 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.400 | -0.200 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | 0.600 | 0.400 | -0.200 |
| gpt-oss-120b | -0.600 | 0.400 | +1.000 |
| gpt-oss-20b | 0.200 | 0.000 | -0.200 |
| kimi-k3 | 0.600 | 0.400 | -0.200 |
| mimo-v2.6-flash | 0.600 | 0.400 | -0.200 |
| nemotron-3-super | 0.600 | 0.400 | -0.200 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 0.800 | +0.000 |
| gemma-4-31b | 0.800 | 0.800 | +0.000 |
| glm-5.3-flash | 0.800 | 0.800 | +0.000 |
| gpt-oss-120b | 0.000 | 0.800 | +0.800 |
| gpt-oss-20b | 0.600 | 0.200 | -0.400 |
| kimi-k3 | 0.800 | -0.600 | -1.400 |
| mimo-v2.6-flash | 0.800 | 0.800 | +0.000 |
| nemotron-3-super | 0.800 | 0.800 | +0.000 |
| qwen3.5-122b | 0.800 | 0.800 | +0.000 |
| qwen3.6-27b | 0.800 | 0.800 | +0.000 |
| qwen3.8-27b | 0.800 | 0.800 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 0.000 | 0.000 | +0.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | -1.000 | 1.000 | +2.000 |
| nemotron-3-super | 1.000 | 0.000 | -1.000 |
| qwen3.5-122b | 1.000 | 0.000 | -1.000 |
| qwen3.6-27b | 1.000 | 0.000 | -1.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 0.667 | -0.333 |
| gpt-oss-20b | 1.000 | 0.667 | -0.333 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.333 | 1.000 | +0.667 |
| nemotron-3-super | 0.333 | 1.000 | +0.667 |
| qwen3.5-122b | 1.000 | 0.667 | -0.333 |
| qwen3.6-27b | 1.000 | 0.667 | -0.333 |
| qwen3.8-27b | 1.000 | 0.000 | -1.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | -0.400 | -1.400 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 0.800 | 1.000 | +0.200 |
| nemotron-3-super | 0.800 | 1.000 | +0.200 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 0.667 | -0.333 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 0.667 | -0.333 |
| gpt-oss-120b | 1.000 | 0.333 | -0.667 |
| gpt-oss-20b | 0.000 | 0.667 | +0.667 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 0.667 | 0.667 | +0.000 |
| qwen3.5-122b | 1.000 | 0.667 | -0.333 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -1.000 | 1.000 | +2.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | -0.667 | 0.333 | +1.000 |
| gpt-oss-120b | 1.000 | 0.333 | -0.667 |
| gpt-oss-20b | 1.000 | 0.000 | -1.000 |
| kimi-k3 | 1.000 | 0.667 | -0.333 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 0.667 | -0.333 |
| qwen3.6-27b | 1.000 | 0.000 | -1.000 |
| qwen3.8-27b | 1.000 | 0.333 | -0.667 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 0.200 | -0.800 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 0.600 | -0.400 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 1.000 | +0.000 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | -0.200 | -1.200 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 1.000 | +0.000 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 1.000 | +0.000 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | 0.333 | +0.000 |
| gemma-4-31b | 0.333 | 0.000 | -0.333 |
| glm-5.3-flash | -0.667 | 0.333 | +1.000 |
| gpt-oss-120b | 0.333 | -0.667 | -1.000 |
| gpt-oss-20b | -0.667 | -0.667 | +0.000 |
| kimi-k3 | 0.333 | 0.000 | -0.333 |
| mimo-v2.6-flash | 0.333 | 0.000 | -0.333 |
| nemotron-3-super | -0.667 | -0.333 | +0.334 |
| qwen3.5-122b | 0.333 | -0.667 | -1.000 |
| qwen3.6-27b | -0.667 | 0.000 | +0.667 |
| qwen3.8-27b | 0.333 | 0.000 | -0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.400 | -0.200 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | 0.600 | 0.400 | -0.200 |
| gpt-oss-120b | 0.600 | 0.400 | -0.200 |
| gpt-oss-20b | 0.200 | 0.400 | +0.200 |
| kimi-k3 | 0.600 | 0.400 | -0.200 |
| mimo-v2.6-flash | 0.200 | 0.400 | +0.200 |
| nemotron-3-super | 0.600 | 0.400 | -0.200 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.400 | -0.200 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | 0.600 | 0.400 | -0.200 |
| gpt-oss-120b | 0.600 | 0.400 | -0.200 |
| gpt-oss-20b | 0.000 | 0.600 | +0.600 |
| kimi-k3 | 0.600 | 0.400 | -0.200 |
| mimo-v2.6-flash | 0.600 | 0.600 | +0.000 |
| nemotron-3-super | 0.600 | 0.200 | -0.400 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | -0.667 | -1.000 |
| gemma-4-31b | 0.667 | -0.667 | -1.334 |
| glm-5.3-flash | 0.667 | 1.000 | +0.333 |
| gpt-oss-120b | 0.667 | 1.000 | +0.333 |
| gpt-oss-20b | 0.667 | 1.000 | +0.333 |
| kimi-k3 | 0.667 | 1.000 | +0.333 |
| mimo-v2.6-flash | 0.333 | -0.333 | -0.666 |
| nemotron-3-super | 0.667 | 1.000 | +0.333 |
| qwen3.5-122b | 0.667 | -0.333 | -1.000 |
| qwen3.6-27b | -0.333 | 0.000 | +0.333 |
| qwen3.8-27b | 0.667 | 1.000 | +0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.600 | +0.000 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | 0.600 | 0.400 | -0.200 |
| gpt-oss-120b | 0.600 | 0.400 | -0.200 |
| gpt-oss-20b | 0.600 | 0.000 | -0.600 |
| kimi-k3 | 0.600 | 0.400 | -0.200 |
| mimo-v2.6-flash | 0.600 | 0.400 | -0.200 |
| nemotron-3-super | 0.600 | 0.400 | -0.200 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.000 | 0.400 | +0.400 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | -0.667 | -0.667 |
| gemma-4-31b | 0.000 | -0.667 | -0.667 |
| glm-5.3-flash | 1.000 | 0.000 | -1.000 |
| gpt-oss-120b | -0.667 | -0.667 | +0.000 |
| kimi-k3 | -0.667 | -0.667 | +0.000 |
| mimo-v2.6-flash | 0.000 | 0.000 | +0.000 |
| nemotron-3-super | -0.333 | -0.333 | +0.000 |
| qwen3.5-122b | -0.667 | -0.667 | +0.000 |
| qwen3.6-27b | -0.667 | 0.000 | +0.667 |
| qwen3.8-27b | -0.667 | -0.667 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | -0.333 | 0.067 | +0.400 |
| gemma-4-31b | -0.333 | -0.467 | -0.134 |
| glm-5.3-flash | -0.333 | -0.733 | -0.400 |
| gpt-oss-120b | -0.333 | -0.733 | -0.400 |
| gpt-oss-20b | -0.333 | -0.200 | +0.133 |
| kimi-k3 | -0.333 | -0.733 | -0.400 |
| mimo-v2.6-flash | -0.333 | -0.467 | -0.134 |
| nemotron-3-super | -0.333 | -0.733 | -0.400 |
| qwen3.5-122b | -0.333 | -0.333 | +0.000 |
| qwen3.6-27b | -0.333 | -0.733 | -0.400 |
| qwen3.8-27b | -0.333 | -0.733 | -0.400 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 0.600 | -0.200 |
| gemma-4-31b | 0.800 | 0.600 | -0.200 |
| glm-5.3-flash | 0.800 | 1.000 | +0.200 |
| gpt-oss-120b | 0.800 | 1.000 | +0.200 |
| gpt-oss-20b | 0.800 | 0.000 | -0.800 |
| kimi-k3 | 0.800 | 1.000 | +0.200 |
| mimo-v2.6-flash | 0.800 | -0.400 | -1.200 |
| nemotron-3-super | 0.800 | 0.600 | -0.200 |
| qwen3.5-122b | 0.800 | 0.200 | -0.600 |
| qwen3.6-27b | 0.800 | 1.000 | +0.200 |
| qwen3.8-27b | 0.800 | 1.000 | +0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.600 | 0.400 | -0.200 |
| gemma-4-31b | 0.600 | 0.400 | -0.200 |
| glm-5.3-flash | 0.600 | 0.400 | -0.200 |
| gpt-oss-120b | 0.600 | 0.400 | -0.200 |
| gpt-oss-20b | 0.600 | 0.000 | -0.600 |
| kimi-k3 | 0.600 | 0.400 | -0.200 |
| mimo-v2.6-flash | 0.600 | 0.400 | -0.200 |
| nemotron-3-super | 0.600 | 0.600 | +0.000 |
| qwen3.5-122b | 0.600 | 0.400 | -0.200 |
| qwen3.6-27b | 0.600 | 0.400 | -0.200 |
| qwen3.8-27b | 0.600 | 0.400 | -0.200 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | 0.333 | +0.333 |
| gemma-4-31b | 0.333 | 0.000 | -0.333 |
| glm-5.3-flash | 0.333 | 0.000 | -0.333 |
| gpt-oss-120b | 0.333 | 0.000 | -0.333 |
| gpt-oss-20b | 0.333 | 0.000 | -0.333 |
| kimi-k3 | 0.333 | 0.000 | -0.333 |
| mimo-v2.6-flash | 0.333 | 0.333 | +0.000 |
| nemotron-3-super | 0.333 | 0.000 | -0.333 |
| qwen3.5-122b | 0.333 | 0.000 | -0.333 |
| qwen3.6-27b | 0.333 | 0.000 | -0.333 |
| qwen3.8-27b | 0.333 | 0.000 | -0.333 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | 1.000 | +0.000 |
| gemma-4-31b | 1.000 | 0.400 | -0.600 |
| glm-5.3-flash | 1.000 | 1.000 | +0.000 |
| gpt-oss-120b | 1.000 | 1.000 | +0.000 |
| gpt-oss-20b | 1.000 | 0.000 | -1.000 |
| kimi-k3 | 1.000 | 1.000 | +0.000 |
| mimo-v2.6-flash | 1.000 | 0.400 | -0.600 |
| nemotron-3-super | 1.000 | 1.000 | +0.000 |
| qwen3.5-122b | 1.000 | 0.400 | -0.600 |
| qwen3.6-27b | 1.000 | 1.000 | +0.000 |
| qwen3.8-27b | 1.000 | 1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.800 | 0.800 | +0.000 |
| gemma-4-31b | 0.800 | 0.800 | +0.000 |
| glm-5.3-flash | 0.800 | 0.800 | +0.000 |
| gpt-oss-120b | 0.800 | 0.000 | -0.800 |
| gpt-oss-20b | 0.800 | 0.000 | -0.800 |
| kimi-k3 | 0.800 | 0.800 | +0.000 |
| mimo-v2.6-flash | 0.800 | 0.800 | +0.000 |
| nemotron-3-super | 0.800 | 0.800 | +0.000 |
| qwen3.5-122b | 0.800 | 0.800 | +0.000 |
| qwen3.6-27b | 0.800 | 0.000 | -0.800 |
| qwen3.8-27b | 0.800 | 0.000 | -0.800 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | -0.667 | -0.667 |
| gemma-4-31b | -0.333 | -0.667 | -0.334 |
| glm-5.3-flash | -0.333 | -0.667 | -0.334 |
| gpt-oss-120b | -0.333 | -0.667 | -0.334 |
| kimi-k3 | -0.333 | -0.667 | -0.334 |
| mimo-v2.6-flash | -0.333 | -1.000 | -0.667 |
| nemotron-3-super | -0.333 | -0.667 | -0.334 |
| qwen3.5-122b | -0.333 | -0.667 | -0.334 |
| qwen3.6-27b | -0.333 | -0.667 | -0.334 |
| qwen3.8-27b | -0.333 | -0.667 | -0.334 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.000 | -0.667 | -0.667 |
| gemma-4-31b | 0.000 | -0.667 | -0.667 |
| glm-5.3-flash | -0.333 | -0.667 | -0.334 |
| gpt-oss-120b | -0.333 | -0.667 | -0.334 |
| gpt-oss-20b | -0.333 | -0.333 | +0.000 |
| kimi-k3 | 0.000 | -0.667 | -0.667 |
| mimo-v2.6-flash | 0.000 | -0.667 | -0.667 |
| nemotron-3-super | -0.333 | -0.667 | -0.334 |
| qwen3.5-122b | 0.000 | -0.667 | -0.667 |
| qwen3.6-27b | 0.000 | -0.667 | -0.667 |
| qwen3.8-27b | -0.333 | -0.667 | -0.334 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.238 | -0.333 | -0.571 |
| gemma-4-31b | 0.238 | -0.333 | -0.571 |
| glm-5.3-flash | 0.238 | -0.333 | -0.571 |
| gpt-oss-120b | 0.238 | -0.333 | -0.571 |
| gpt-oss-20b | 0.143 | 0.143 | +0.000 |
| kimi-k3 | 0.238 | -0.333 | -0.571 |
| mimo-v2.6-flash | 0.238 | -0.333 | -0.571 |
| nemotron-3-super | 0.238 | -0.333 | -0.571 |
| qwen3.5-122b | 0.238 | -0.333 | -0.571 |
| qwen3.6-27b | 0.238 | -0.333 | -0.571 |
| qwen3.8-27b | 0.238 | -0.333 | -0.571 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.667 | 0.000 | -0.667 |
| gemma-4-31b | 0.667 | 0.000 | -0.667 |
| glm-5.3-flash | 0.667 | 0.333 | -0.334 |
| gpt-oss-120b | 0.667 | 0.333 | -0.334 |
| gpt-oss-20b | 0.333 | 0.333 | +0.000 |
| kimi-k3 | 0.667 | -0.333 | -1.000 |
| mimo-v2.6-flash | 0.333 | -0.667 | -1.000 |
| nemotron-3-super | 0.333 | 0.333 | +0.000 |
| qwen3.5-122b | -0.667 | 0.000 | +0.667 |
| qwen3.6-27b | 1.000 | -0.667 | -1.667 |
| qwen3.8-27b | 0.667 | -0.667 | -1.334 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 1.000 | -1.000 | -2.000 |
| gemma-4-31b | 1.000 | -1.000 | -2.000 |
| glm-5.3-flash | -1.000 | 1.000 | +2.000 |
| gpt-oss-120b | 1.000 | -1.000 | -2.000 |
| gpt-oss-20b | -0.667 | 1.000 | +1.667 |
| kimi-k3 | 1.000 | -1.000 | -2.000 |
| mimo-v2.6-flash | -0.667 | 1.000 | +1.667 |
| nemotron-3-super | 0.000 | -1.000 | -1.000 |
| qwen3.5-122b | 1.000 | -1.000 | -2.000 |
| qwen3.6-27b | 1.000 | -1.000 | -2.000 |
| qwen3.8-27b | -1.000 | -1.000 | +0.000 |
| Model | Grids Only τ | + Narrative τ | Lift |
|---|---|---|---|
| gemma-4-26b | 0.333 | -0.667 | -1.000 |
| gemma-4-31b | 0.333 | -0.667 | -1.000 |
| glm-5.3-flash | 0.333 | -0.667 | -1.000 |
| gpt-oss-120b | 0.333 | -0.667 | -1.000 |
| kimi-k3 | 0.333 | -1.000 | -1.333 |
| mimo-v2.6-flash | 0.333 | -1.000 | -1.333 |
| nemotron-3-super | 0.333 | -1.000 | -1.333 |
| qwen3.5-122b | 0.333 | -0.667 | -1.000 |
| qwen3.6-27b | 0.333 | -0.667 | -1.000 |
| qwen3.8-27b | 0.333 | -1.000 | -1.333 |