Benchmark
Apex-Agent · Pass@1
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 1
- Scores recorded
- 1
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 25.6%
- Mean
- 25.6%
- Median
- 0%
- Std dev
- 25.6%
- 10th percentile
- 25.6%
- 90th percentile
- 25.6%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted · pass@1· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 25.6% |