Benchmark
Chartography · With tools
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 7
- Scores recorded
- 7
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 75.6%
- Mean
- 86.2%
- Median
- 27.4%
- Std dev
- 83%
- 10th percentile
- 89%
- 90th percentile
- 8.8%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · container + crop tool · adaptive thinking · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 90.2% |
| 2 | Claude Opus 5.5Opus 5.5 System Card capability section · container + crop tool · adaptive thinking · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 89% |
| 3 | Claude Fable 5.1Opus 5.5 System Card capability section · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.4% |
| 4 | Claude Haiku 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · container + crop tool · adaptive thinking · max · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.2% |
| 5 | Claude Opus 5Opus 5.5 System Card capability section · with tools· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83.4% |
| 6 | DeepSeek V4.1 Flash 1017DeepSeek 1017 first-party evaluation · reasoning effort, candidate sampling, exact run count, and unspecified harnesses not published · with tools · harness unspecified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83% |
| 7 | Claude Haiku 4.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · container + crop tool · fixed thinking budget · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 8.8% |