Skip to content

Benchmark

FigQA

Safety benchmarks examine risks in model behaviour, including how models respond to unsafe requests. Scores are percentages.

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

Score distribution

56.2%
Mean
78.3%
Median
22.2%
Std dev
34%
10th percentile
78.3%
90th percentile
34%
Min
34%78.3%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78.3%
2Grok 4.1thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim34%

Data credits: Data by LLM Stats