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
1Claude 3 Haiku· Stanford HELM specialized suites data docs100%
2Claude 3 Sonnet· Stanford HELM specialized suites data docs100%
3Claude 3.5 Sonnetsetting not named by the source· Stanford HELM specialized suites data docs100%
4Claude Haiku 4.5· Stanford HELM specialized suites data docs100%
5Claude Sonnet 4.5· Stanford HELM specialized suites data docs100%
6GPT 5· Stanford HELM specialized suites data docs100%
7GPT OSS 120B· Stanford HELM specialized suites data docs100%
8GPT OSS 20b· Stanford HELM specialized suites data docs100%
9GPT-5 mini· Stanford HELM specialized suites data docs100%
10GPT-5 nano· Stanford HELM specialized suites data docs100%
11Llama3 8B Chat· Stanford HELM specialized suites data docs100%
12o1· Stanford HELM specialized suites data docs100%
13o3 Mini· Stanford HELM specialized suites data docs100%
14OpenAI o3· Stanford HELM specialized suites data docs100%
15Qwen3 Next 80B A3Bthinking· Stanford HELM specialized suites data docs100%
16Claude 3 Opus· Stanford HELM specialized suites data docs93.3%
17Claude 3.5 Sonnetsetting not named by the source· Stanford HELM specialized suites data docs93.3%
18Claude Opus 4· Stanford HELM specialized suites data docs93.3%
19Claude Sonnet 3.7· Stanford HELM specialized suites data docs93.3%
20Claude Sonnet 4· Stanford HELM specialized suites data docs93.3%
21Gemini 2.0 Flash-Lite Preview· Stanford HELM specialized suites data docs93.3%
22Gemini 2.5 Flash-Lite· Stanford HELM specialized suites data docs93.3%
23Gemini 2.5 Pro Preview 03-25· Stanford HELM specialized suites data docs93.3%
24Gemini 3 Pro Preview· Stanford HELM specialized suites data docs93.3%
25gemini-2.0-pro-exp-02-05· Stanford HELM specialized suites data docs93.3%
26GPT 4· Stanford HELM specialized suites data docs93.3%
27GPT 4.1· Stanford HELM specialized suites data docs93.3%
28GPT 5.1· Stanford HELM specialized suites data docs93.3%
29GPT-4 Turbo· Stanford HELM specialized suites data docs93.3%
30Granite 3.3 8b Instruct· Stanford HELM specialized suites data docs93.3%
31Granite 4.0 H Small· Stanford HELM specialized suites data docs93.3%
32Kimi K2 Instruct· Stanford HELM specialized suites data docs93.3%
33Llama 4 Maverick· Stanford HELM specialized suites data docs93.3%
34o4 Mini· Stanford HELM specialized suites data docs93.3%
35Palmyra X5· Stanford HELM specialized suites data docs93.3%
36Qwen3 235B A22B Instruct 2507· Stanford HELM specialized suites data docs93.3%
37DeepSeek R1· Stanford HELM specialized suites data docs86.7%
38Gemini 2.0 Flash· Stanford HELM specialized suites data docs86.7%
39gemini-1.5-flash-002· Stanford HELM specialized suites data docs86.7%
40gemini-1.5-pro-002· Stanford HELM specialized suites data docs86.7%
41GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs86.7%
42GPT-4.1 mini· Stanford HELM specialized suites data docs86.7%
43GPT-4.1 nano· Stanford HELM specialized suites data docs86.7%
44GPT-4.5 Preview· Stanford HELM specialized suites data docs86.7%
45GPT-4o mini· Stanford HELM specialized suites data docs86.7%
46Llama 3.1 8B Instruct Turbo· Stanford HELM specialized suites data docs86.7%
47Qwen2.5 72B Instruct Turbo· Stanford HELM specialized suites data docs86.7%
48gemini-2.5-flash-preview-04-17· Stanford HELM specialized suites data docs80%
49Grok 3 Mini· Stanford HELM specialized suites data docs80%
50Qwen2 72B Instruct· Stanford HELM specialized suites data docs80%

Showing 1–50 of 75 results.

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