Benchmark
FigQA
Safety benchmarks examine risks in model behaviour, including how models respond to unsafe requests. Scores are percentages.
All safety benchmarksScores from LLM Stats data.
- 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
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78.3% |
| 2 | Grok 4.1thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34% |
Data credits: Data by LLM Stats