LiveBench Olympiad: leaderboard
The LiveBench math task built from proof-based USAMO and IMO problems, refreshed over time with newer competitions. Formulae are cut out of a written solution and handed back to the model in scrambled order, and it must say which formula fills each gap. Scoring is automatic, by edit distance between its ordering and the true one with no judge model, and higher is better.
Metric: Score. Source: livebench.ai. Saturation forecast: Estimated already saturated. 71 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 5.5 (Max) | 93.25 | #3 (Claude Opus 5.5) |
| 2 | Claude Fable 5.1 (Max) | 92.97 | #9 (Claude Fable 5.1) |
| 3 | Claude Fable 5 (Max) | 92.84 | #16 (Claude Fable 5) |
| 4 | Claude Opus 5 (Max) | 92.8 | #12 (Claude Opus 5) |
| 5 | Claude Sonnet 5.5 (Max) | 92.47 | #11 (Claude Sonnet 5.5) |
| 6 | GPT-6.1 Sol (Max) | 92.27 | #7 (GPT-6.1 Sol) |
| 7 | Claude Opus 4.8 (Max) | 92.23 | #37 (Claude Opus 4.8) |
| 8 | GPT-6 Astra (Max) | 92.17 | #6 (GPT-6 Astra) |
| 9 | Claude Opus 4.6 (Thinking, High) | 92.17 | #63 (Claude Opus 4.6) |
| 10 | Gemini 3.8 Flash (High) | 92.16 | #21 (Gemini 3.8 Flash) |
| 11 | Claude Opus 5.5 (xHigh) | 92.15 | #3 (Claude Opus 5.5) |
| 12 | Gemini 3.1 Pro (Preview) (High) | 92.1 | #58 (Gemini 3.1 Pro (Preview)) |
| 13 | Gemini 3.5 Flash (High) | 91.88 | #60 (Gemini 3.5 Flash) |
| 14 | GPT-6.1 Sol (xHigh) | 91.86 | #7 (GPT-6.1 Sol) |
| 15 | Muse Wonder (Max) | 91.82 | #15 (Muse Wonder) |
No result here: #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=livebench-olympiad · How It Works · Data refreshed daily, snapshot 2026-10-20.