Open LLM Leaderboard - BBH: leaderboard
The "BBH" subtask of Open LLM Leaderboard. A task from the Open LLM Leaderboard, the standard open-weight evaluation suite spanning knowledge, reasoning, math and truthfulness benchmarks.
Metric: Score. Source: huggingface.co. Saturation forecast: Estimated already saturated. 4576 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | internlm2.5-20B-chat | 74.74 | #788 |
| 2 | calme-3.2-instruct-78B | 73.19 | #354 |
| 3 | Qwen 2.5 72B Instruct | 72.73 | #470 |
| 4 | InternLM2.5-Chat-7B | 70.73 | #1010 |
| 5 | Rombos-LLM-V2.5-Qwen-32B | 70.46 | #371 |
| 6 | oxyge1-33B | 70.33 | #697 |
| 7 | Qwen 2 72B Instruct | 69.77 | #580 |
| 8 | Awqward2.5-32B-Instruct | 69.74 | #370 |
| 9 | Qwentile2.5-32B-Instruct | 69.63 | #345 |
| 10 | Qwen 2 VL 72B Instruct | 69.46 | #551 |
| 11 | Qwen2.5-32B-Instruct-abliterated-v2 | 69.34 | #400 |
| 12 | Llama 3.3 70B Instruct | 69.19 | #541 |
| 13 | Llama 3.1 70B Instruct | 69.17 | #574 |
| 14 | Qwen 2.5 32B Instruct | 69.13 | #511 |
| 15 | solar-pro-preview-instruct | 68.17 | #755 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #6 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-llm-leaderboard-bbh · How It Works · Data refreshed daily, snapshot 2026-11-06.