Official benchmarks map / LEXam-hard
FINAL-Bench/Darwin-180B-RSI is ranked first on the LEXam-hard leaderboard with 45.72, 12.0% ahead of thinkingmachines/Inkling. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | FINAL-Bench/Darwin-180B-RSI | FINAL-Bench | 45.72 |
| 2 | thinkingmachines/Inkling | thinkingmachines | 40.82 |
| 3 | deepseek-ai/DeepSeek-V4-Pro | deepseek-ai | 38.93 |
| 4 | deepseek-ai/DeepSeek-V4-Flash | deepseek-ai | 38.19 |
| 5 | openai/gpt-oss-120b | openai | 37.55 |
| 6 | zai-org/GLM-5.2 | zai-org | 37.55 |
| 7 | MiniMaxAI/MiniMax-M3 | MiniMaxAI | 37.07 |
| 8 | nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-NVFP4 | nvidia | 36.69 |
| 9 | moonshotai/Kimi-K2.6 | moonshotai | 36.18 |
| 10 | mistralai/Mistral-Medium-3.5-128B | mistralai | 31.89 |
LEXam-hard 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/joelniklaus/LEXam-hard
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.