Skip to content

Benchmark

HELM AIR-Bench: AIRBench 2024 - #19: Non-Consensual Nudity

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

Models measured
70
Scores recorded
75
Sources
1
IQ weight
1.82

Score distribution

78.5%
Mean
86.7%
Median
24.5%
Std dev
46.7%
10th percentile
100%
90th percentile
0%
Min
0%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.82 for chat models, measured over 70 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs76.7%
52GLM 4.5 Air· Stanford HELM specialized suites data docs73.3%
53GPT 4osetting not named by the source· Stanford HELM specialized suites data docs73.3%
54Llama 4 Scout· Stanford HELM specialized suites data docs70%
55GPT 4osetting not named by the source· Stanford HELM specialized suites data docs66.7%
56Llama 3.1 405B Instruct Turbo· Stanford HELM specialized suites data docs66.7%
57Qwen1.5-72B-Chat· Stanford HELM specialized suites data docs66.7%
58Yi 34B Chat· Stanford HELM specialized suites data docs66.7%
59GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs60%
60Meta Llama 3.1 70B Instruct Turbo· Stanford HELM specialized suites data docs60%
61DeepSeek LLM 67B Chat· Stanford HELM specialized suites data docs53.3%
62DeepSeek V3· Stanford HELM specialized suites data docs53.3%
63GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs53.3%
64Grok 3· Stanford HELM specialized suites data docs53.3%
65Grok 4· Stanford HELM specialized suites data docs53.3%
66Qwen2.5 7B Instruct Turbo· Stanford HELM specialized suites data docs53.3%
67Mistral Large2407· Stanford HELM specialized suites data docs46.7%
68O1 Mini· Stanford HELM specialized suites data docs46.7%
69Command R+· Stanford HELM specialized suites data docs40%
70Mixtral 8x7B Instruct v0.1· Stanford HELM specialized suites data docs33.3%
71Command R Plus· Stanford HELM specialized suites data docs26.7%
72Mistral Small· Stanford HELM specialized suites data docs26.7%
73Mixtral 8x22B Instruct v0.1· Stanford HELM specialized suites data docs13.3%
74DBRX-instruct· Stanford HELM specialized suites data docs0%
75Mistral (7B) Instruct v0.3· Stanford HELM specialized suites data docs0%

Showing 51–75 of 75 results.

Data credits: Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance