Epoch AI - Ebr Bench: leaderboard
Metric: Score. Source: epoch.ai. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 (Max) | 76.19 |
| 2 | Claude Opus 5 (Max) | 50 |
| 3 | Claude Fable 5.1 (Max) | 47.62 |
| 4 | Claude Fable 5 (Max) | 39.52 |
| 5 | GPT-5.6 Sol (Max) | 39.05 |
| 6 | GPT-5.5 (xHigh) | 34.29 |
| 7 | Grok 4.6 (xHigh) | 30.48 |
| 8 | Claude Opus 4.8 (Max) | 28.57 |
| 9 | GPT-5.4 (xHigh) | 25.4 |
| 10 | GPT-5.2 (xHigh) | 23.02 |
| 11 | Claude Opus 4.7 (Max) | 19.05 |
| 12 | Gemini 3.1 Pro (Preview) | 14.29 |
| 13 | GPT-5 (High) | 12.7 |
| 14 | Claude Opus 4.6 (Max) | 12.7 |
| 15 | Qwen 3.7 Max | 9.52 |
Interactive version: theaggregate.ai/benchmark?slug=epoch-ai-ebr-bench · How It Works · Data refreshed daily, snapshot 2026-09-05.