Official benchmarks map / safeagents-judge-bench
vllm-sr/d3-ultra is ranked first on the safeagents-judge-bench leaderboard with 0.76, 5.3% ahead of vllm-sr/d3-turbo. Read live from the Hugging Face API on November 8, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | vllm-sr/d3-ultra | vllm-sr | 0.76 |
| 2 | vllm-sr/d3-turbo | vllm-sr | 0.72 |
safeagents-judge-bench 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/harness-hub/safeagents-judge-bench
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.