Official benchmarks map / SWE-bench_Pro
PCL-RSI-lab/Seshat-agent is ranked first on the SWE-bench_Pro leaderboard with 94.94, 38.1% ahead of inclusionAI/Ling-3.1-flash. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | PCL-RSI-lab/Seshat-agent | PCL-RSI-lab | 94.94 |
| 2 | inclusionAI/Ling-3.1-flash | inclusionAI | 68.74 |
| 3 | Qwen/Qwen3.8-2.4T-A95B | Qwen | 67.7 |
| 4 | reflection/Beam-1.0-501B-A23B | reflection | 66.1 |
| 5 | tencent/Hy4-preview | tencent | 65.7 |
| 6 | ornith-ai/Ornith-1.5-397B | ornith-ai | 65.1 |
| 7 | nitrai-research/Moderato-V1-Pro | nitrai-research | 63.3 |
| 8 | Qwen/Qwen3.8-Flash-Next | Qwen | 62.5 |
| 9 | ornith-ai/Ornith-1.0-397B | ornith-ai | 62.2 |
| 10 | zai-org/GLM-5.2 | zai-org | 62.1 |
SWE-bench_Pro 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/ScaleAI/SWE-bench_Pro
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.