BenchBench: leaderboard
Meta-benchmark leaderboard aggregating how well models perform across benchmark-oriented evaluation tasks.
Metric: Aggregate Score (%). Source: huggingface.co. Saturation forecast: Estimated already saturated. 137 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o (2024-05-13) | 97.67 | #325 |
| 2 | GPT-4o ChatGPT | 97.54 | |
| 3 | GPT-4o (2024-08-06) | 96.53 | #336 |
| 4 | Claude 3.5 Sonnet (20240620) | 95.73 | #299 |
| 5 | Llama 3.1 70B Instruct | 93.43 | #561 |
| 6 | GPT-4 Turbo | 90.56 | #404 |
| 7 | Claude 3 Opus (20240229) | 88.24 | #412 |
| 8 | Llama 3.1 405B Instruct | 85.98 | #457 |
| 9 | GPT-4 Preview (0125) | 84.92 | #486 |
| 10 | Hermes 3 - Llama-3.1 70B | 84.51 | #927 |
| 11 | Mistral Large 2 (Jul) | 83.75 | #484 |
| 12 | GPT-4o Mini (2024-07-18) | 83.49 | #558 |
| 13 | Claude 2 | 83.33 | #761 |
| 14 | Gemini 1.5 Pro (0514) | 82.95 | #512 |
| 15 | Llama 3 70B Instruct | 81.73 | #634 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=benchbench · How It Works · Data refreshed daily, snapshot 2026-10-20.