COHERENCE - WikiHow: 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 WikiHow procedural documents, in percent; higher is better.
Metric: Exact-match accuracy (%) on the 2,076 WikiHow procedural 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) | 80.73 | #99 | |
| 2 | GPT-5.4 | High | 77.5 | #135 |
| 3 | Doubao-Seed-2.0-Pro-260215 | 76.59 | #158 | |
| 4 | Kimi K2.5 | 75.67 | #266 | |
| 5 | Claude Sonnet 4.6 | Thinking | 74.18 | #173 |
| 6 | Doubao-Seed-2.0-Lite-260215 | 72.74 | #262 | |
| 7 | Qwen 3.5 122B A10B | 71.87 | #346 | |
| 8 | Doubao-Seed-2.0-Mini-260215 | 70.81 | ||
| 9 | Qwen 3.5 397B A17B | 69.85 | #264 | |
| 10 | Qwen 3.5 35B A3B | 69.7 | #492 | |
| 11 | GPT-5.2 | 68.5 | #185 | |
| 12 | Qwen 3 VL 235B A22B | 64.45 | #485 | |
| 13 | Intern-S1-Pro | 64.26 | #585 | |
| 14 | GLM-4.6V | 62.96 | #710 | |
| 15 | Qwen 3.5 4B | 62.76 | #1241 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=coherence-wikihow · How It Works · Data refreshed daily, snapshot 2026-11-21.