OMIBench: leaderboard
OMIBench (2026) tests vision-language models on Olympiad-level science and mathematics problems whose evidence is spread across several images. This board is the GPTScore in percent, the share of answers an LLM judge finds equivalent to the gold answer, over all problems; higher is better.
Metric: GPTScore (%, binarized LLM-judge equivalence of the final answer with the gold answer, micro-averaged) on the 1,322 problems of OMIBench (Olympiad-level multi-image problems from biology, chemistry, mathematics and physics competitions), zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 37 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 50.53 | #123 |
| 2 | Qwen 3 VL 32B (Thinking) | 49.54 | #577 |
| 3 | GPT-5 | 48.11 | #185 |
| 4 | GPT-5 Mini | 47.73 | #373 |
| 5 | Qwen 3 VL 30B A3B (Thinking) | 47.2 | #727 |
| 6 | Qwen 3 VL 235B A22B (Thinking) | 47.05 | #462 |
| 7 | O4 Mini | 45.97 | #372 |
| 8 | Gemini 2.5 Pro | 44.1 | #280 |
| 9 | Qwen 3 VL 8B (Thinking) | 38.65 | #924 |
| 10 | Qwen 3 VL 32B Instruct | 35.78 | #607 |
| 11 | Gemini 2.5 Flash | 35.25 | #466 |
| 12 | Qwen 3 VL 235B A22B Instruct | 34.39 | #541 |
| 13 | Qwen 3 VL 4B (Thinking) | 30.03 | #1354 |
| 14 | Qwen 3 VL 30B A3B Instruct | 28.59 | #903 |
| 15 | Qwen 2.5 VL 72B Instruct | 27.99 | #849 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=omibench · How It Works · Data refreshed daily, snapshot 2026-11-22.