Open LLM Leaderboard - MuSR: leaderboard
The "MuSR" 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 | calme-3.2-instruct-78B | 60.24 | #347 |
| 2 | DeepSeek R1 Distill Qwen 14B | 53.66 | #844 |
| 3 | Orca-2-13B | 51.3 | #1448 |
| 4 | free-solar-evo-v0.13 | 50.52 | #1080 |
| 5 | free-solar-evo-v0.11 | 50.52 | #1128 |
| 6 | phi-4-14B | 50.47 | #733 |
| 7 | Phi-4 | 50.34 | #706 |
| 8 | Rombos-LLM-V2.5-Qwen-32B | 50.34 | #367 |
| 9 | Orca-2-7B | 50.26 | #1502 |
| 10 | oxyge1-33B | 50.08 | #690 |
| 11 | Llama-3.1-Tulu-3-70B | 49.88 | #482 |
| 12 | neural-chat-7B-v3-1 | 49.79 | #1307 |
| 13 | Qwen 2.5 32B | 49.78 | #546 |
| 14 | dolphin-2.9.1-llama-3-70B | 49.76 | #722 |
| 15 | Hermes 3 - Llama-3.1 70B | 49.49 | #927 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=open-llm-leaderboard-musr · How It Works · Data refreshed daily, snapshot 2026-10-20.