Official benchmarks map / LEXam
FINAL-Bench/Darwin-180B-RSI is ranked first on the LEXam leaderboard with 68.94, 31.5% ahead of deepseek-ai/DeepSeek-R1. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | FINAL-Bench/Darwin-180B-RSI | FINAL-Bench | 68.94 |
| 2 | deepseek-ai/DeepSeek-R1 | deepseek-ai | 52.41 |
| 3 | Qwen/Qwen3-235B-A22B-Thinking-2507 | Qwen | 48.19 |
| 4 | openai/gpt-oss-120b | openai | 47.71 |
| 5 | deepseek-ai/DeepSeek-V3 | deepseek-ai | 46.57 |
| 6 | Qwen/Qwen3-32B | Qwen | 45.3 |
| 7 | Qwen/Qwen3-Next-80B-A3B-Thinking | Qwen | 43.31 |
| 8 | openai/gpt-oss-20b | openai | 40.78 |
| 9 | microsoft/phi-4 | microsoft | 40.66 |
| 10 | mistralai/Ministral-8B-Instruct-2410 | mistralai | 26.27 |
LEXam is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.
Original board: huggingface.co/datasets/LEXam-Benchmark/LEXam
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.