Skip to content

Benchmark

ProtocolQA Open-Ended

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

53.4%
Mean
70.4%
Median
17%
Std dev
36.4%
10th percentile
70.4%
90th percentile
36.4%
Min
36.4%70.4%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Grok 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.4%
2GPT-rosalind-research· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim36.4%

Data credits: Data by LLM Stats