Benchmark
BenchCAD · Vision2Code voxel IoU · With tools
Higher scores are better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 0.805
- Mean
- 0.926
- Median
- 0.268
- Std dev
- 0.87
- 10th percentile
- 0.963
- 90th percentile
- 0.21
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 1,000-file subset · tools · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 0.963 |
| 2 | Claude Opus 5.5Opus 5.5 System Card capability section · 1,000-file subset · 256×256 renders · tools · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 0.962 |
| 3 | Claude Fable 5.1Opus 5.5 System Card capability section · 1,000-file subset · 256×256 renders · tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 0.926 |
| 4 | Claude Opus 5Opus 5.5 System Card capability section · 1,000-file subset · 256×256 renders · tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 0.899 |
| 5 | Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 1,000-file subset · tools · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 0.87 |
| 6 | Claude Haiku 4.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · 1,000-file subset · tools · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 0.21 |