COHERENCE - StoryBird: leaderboard
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 January 2027. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 63.59 |
| 2 | GPT-5.4 (High) | 57.37 |
| 3 | Qwen 3.5 397B A17B | 55.58 |
| 4 | Claude Sonnet 4.6 (Thinking) | 52.72 |
| 5 | Doubao-Seed-2.0-Pro-260215 | 52.22 |
| 6 | Qwen 3.5 122B A10B | 49.93 |
| 7 | Qwen 3.5 35B A3B | 48.21 |
| 8 | Kimi K2.5 | 46.21 |
| 9 | GPT-5.2 | 37.34 |
| 10 | Qwen 3.5 4B | 36.41 |
| 11 | Qwen 3 VL 235B A22B | 32.12 |
| 12 | GLM-4.6V | 29.18 |
| 13 | Step3 VL 10B | 25.25 |
| 14 | Qwen 3 VL 8B Instruct | 24.18 |
| 15 | Qwen 3 VL 4B Instruct | 22.46 |
Interactive version: theaggregate.ai/benchmark?slug=coherence-storybird · How It Works · Data refreshed daily, snapshot 2026-10-07.