Benchmark
Safeagents Judge Bench
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 5
- Scores recorded
- 5
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 78%
- Mean
- 82.1%
- Median
- 14.3%
- Std dev
- 50.2%
- 10th percentile
- 89.3%
- 90th percentile
- 50.2%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | clef flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 89.3% |
| 2 | Clef Omni· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 87.7% |
| 3 | d3· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 82.1% |
| 4 | Clef 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 80.8% |
| 5 | Joey 1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 50.2% |
Data credits: Hugging Face official benchmark leaderboards; licence varies by benchmark