Benchmark
Anthropic Real-World Law
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 1
- Scores recorded
- 2
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 61%
- Mean
- 65%
- Median
- 4%
- Std dev
- 57%
- 10th percentile
- 65%
- 90th percentile
- 57%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5professional-work win rate · 16K thinking budget· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65% |
| 2 | Claude Sonnet 4.5professional-work win rate · standard mode· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57% |