COHERENCE - StoryBird: leaderboard
COHERENCE (2026) removes the images from 6,161 interleaved image-text documents (WikiHow, StoryBird, cooking recipes, science) and asks the model to put each candidate image back in its place. This board is the exact-match accuracy on the StoryBird story documents, in percent; higher is better.
Metric: Exact-match accuracy (%) on the 1,398 StoryBird story documents; 6,161 interleaved image-text documents whose images were removed: the model assigns each candidate image to its placeholder; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 63.59 | #99 | |
| 2 | GPT-5.4 | High | 57.37 | #135 |
| 3 | Qwen 3.5 397B A17B | 55.58 | #264 | |
| 4 | Claude Sonnet 4.6 | Thinking | 52.72 | #173 |
| 5 | Doubao-Seed-2.0-Pro-260215 | 52.22 | #158 | |
| 6 | Qwen 3.5 122B A10B | 49.93 | #346 | |
| 7 | Qwen 3.5 35B A3B | 48.21 | #492 | |
| 8 | Kimi K2.5 | 46.21 | #266 | |
| 9 | Doubao-Seed-2.0-Lite-260215 | 44.35 | #262 | |
| 10 | Doubao-Seed-2.0-Mini-260215 | 37.98 | ||
| 11 | GPT-5.2 | 37.34 | #185 | |
| 12 | Qwen 3.5 4B | 36.41 | #1241 | |
| 13 | Qwen 3 VL 235B A22B | 32.12 | #485 | |
| 14 | GLM-4.6V | 29.18 | #710 | |
| 15 | Intern-S1-Pro | 28.9 | #585 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=coherence-storybird · How It Works · Data refreshed daily, snapshot 2026-11-21.