Skip to content

Benchmark

Anthropic Real-World Finance

Scores are percentages. Higher is better.

Models measured
2
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

66.5%
Mean
68%
Median
5.2%
Std dev
59.5%
10th percentile
72%
90th percentile
59.5%
Min
59.5%72%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude 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.72%
2Claude 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.68%
3Claude Sonnet 4.6v1 · overall task completion · internal code/tool harness· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.59.5%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.