Riemann-bench: leaderboard
Metric: Score (%). Source: surgehq.ai. 38 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 74.4 |
| 2 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | 68 |
| 3 | Claude Fable 5 (Adaptive Reasoning, Max Effort) | 60 |
| 4 | GPT-5.5 (xHigh) | 55.2 |
| 5 | Gemini 3.8 Flash (High) | 51.2 |
| 6 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 47.2 |
| 7 | GPT-5.4 (xHigh) | 41.6 |
| 8 | Gemini 3.7 Flash (High) | 39.2 |
| 9 | DeepSeek V4 Pro (Max) | 38.4 |
| 10 | Grok 4.5 (High) | 38.4 |
| 11 | Kimi K3 | 37.6 |
| 12 | GPT-5.2 (xHigh) | 37.6 |
| 13 | Gemini 3.5 Flash (High) | 36.8 |
| 14 | Gemini 3.1 Pro (Preview) | 33.6 |
| 15 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | 32.8 |
Interactive version: theaggregate.ai/benchmark?slug=riemann-bench · How It Works · Data refreshed daily, snapshot 2026-09-05.