Benchmark
ClawEval-MM · Pass@3
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 7
- Scores recorded
- 8
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 61.4%
- Mean
- 60.4%
- Median
- 7%
- Std dev
- 57.4%
- 10th percentile
- 64.4%
- 90th percentile
- 52.5%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Qwen3.8 MaxQwen3.8-Max release vision/video table · Pass@3 · at least one pass in three trials· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 77.2% |
| 2 | Qwen 3.8 Flash NextQwen3.8-Flash-Next release/model card · Pass@3 · at least one pass in three trials· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 64.4% |
| 3 | Qwen3.8 FlashClawEval multimodal split · 三次运行中至少一次通过· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 64.4% |
| 4 | Qwen3.8 Omni FlashClawEval multimodal split · 三次运行中至少一次通过· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.4% |
| 5 | Qwen 3.8 27BClawEval multimodal split · 三次运行中至少一次通过· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.4% |
| 6 | Qwen 3.8 27BQwen3.8-27B model card · Pass@3 · at least one pass in three trials· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.4% |
| 7 | Qwen3.7 PlusClawEval multimodal split · 三次运行中至少一次通过· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.4% |
| 8 | Claude Opus 4.6ClawEval multimodal split · 三次运行中至少一次通过 · max effort· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.5% |