Skip to content

Benchmark

Protein design · Sequence generation

Science benchmarks measure how well models answer science questions. Scores are percentages. Higher is better.

Models measured
5
Scores recorded
8
Sources
2
IQ weight
0.50

Score distribution

38.9%
Mean
42.4%
Median
13.8%
Std dev
20.2%
10th percentile
51%
90th percentile
20.2%
Min
20.2%60.2%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.50 for chat models, measured over 5 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

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.60.2%
2Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51%
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.51%
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.42.4%
5Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim33.1%
6Claude Haiku 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.33.1%
7Claude Sonnet 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.20.2%
8Claude 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.20.2%

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