Skip to content

Benchmark

De novo protein binder design

Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.

Models measured
4
Scores recorded
5
Sources
2
IQ weight
No weight published

Score distribution

79.7%
Mean
82.3%
Median
3.8%
Std dev
72.6%
10th percentile
82.6%
90th percentile
72.6%
Min
72.6%82.6%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Opus 5.5Opus 5.5 System Card · adaptive thinking · max effort unless stated· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.6%
2Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.3%
3Claude Sonnet 5.5adaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.82.3%
4Claude Opus 5Opus 5.5 System Card · adaptive thinking · max effort unless stated· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.9%
5Claude Sonnet 5Opus 5.5 System Card · adaptive thinking · max effort unless stated· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72.6%

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. · Data by LLM Stats