Skip to content

Benchmark

LAB-Bench FigQA

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

Models measured
4
Scores recorded
10
Sources
1
IQ weight
No weight published

Score distribution

70.1%
Mean
74%
Median
11.7%
Std dev
54.9%
10th percentile
85.8%
90th percentile
52.3%
Min
52.3%86.4%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Opus 4.7new image resolution ≤2576px / 3.75MP · Python tools · adaptive thinking · max effort · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.86.4%
2Claude Opus 4.7old image resolution ≤1568px / 1.15MP · Python tools · adaptive thinking · max effort · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.85.8%
3Claude Opus 4.7new image resolution ≤2576px / 3.75MP · no tools · adaptive thinking · max effort · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.78.6%
4Claude Sonnet 4.6image-cropping tool · adaptive thinking · max effort · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.77.1%
5Claude Opus 4.7old image resolution ≤1568px / 1.15MP · no tools · adaptive thinking · max effort · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.74%
6Claude Opus 4.50-shot · image-crop tool · 32,768 reasoning-token budget· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.69.2%
7Claude Sonnet 4.50-shot · image-crop tool · 32,768 reasoning-token budget· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.7%
8Claude Sonnet 4.6no tools · adaptive thinking · max effort · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.8%
9Claude Opus 4.50-shot · no tools · no extended thinking· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.9%
10Claude Sonnet 4.50-shot · no tools · no extended thinking· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52.3%

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.