Skip to content

Benchmark

HELM AIR-Bench: AIRBench 2024 - #31: Fraudulent Schemes

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
1.05

Score distribution

70.8%
Mean
76.7%
Median
25.1%
Std dev
33.3%
10th percentile
98.3%
90th percentile
10%
Min
10%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.05 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 3.5 Sonnetsetting not named by the source· Stanford HELM specialized suites data docs100%
2Claude 3.5 Sonnetsetting not named by the source· Stanford HELM specialized suites data docs100%
3Claude Haiku 4.5· Stanford HELM specialized suites data docs100%
4Claude Sonnet 4· 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-5 mini· Stanford HELM specialized suites data docs100%
8Claude Opus 4· Stanford HELM specialized suites data docs98.3%
9Claude 3 Sonnet· Stanford HELM specialized suites data docs96.7%
10GPT 5.1· Stanford HELM specialized suites data docs96.7%
11GPT OSS 20b· Stanford HELM specialized suites data docs96.7%
12GPT-5 nano· Stanford HELM specialized suites data docs96.7%
13Granite 3.3 8b Instruct· Stanford HELM specialized suites data docs96.7%
14Qwen3 Next 80B A3Bthinking· Stanford HELM specialized suites data docs96.7%
15Claude 3 Opus· Stanford HELM specialized suites data docs95%
16Claude 3 Haiku· Stanford HELM specialized suites data docs93.3%
17Claude Sonnet 3.7· Stanford HELM specialized suites data docs93.3%
18GPT OSS 120B· Stanford HELM specialized suites data docs93.3%
19Kimi K2 Instruct· Stanford HELM specialized suites data docs93.3%
20OpenAI o3· Stanford HELM specialized suites data docs93.3%
21Qwen3 235B A22B Instruct 2507· Stanford HELM specialized suites data docs93.3%
22Llama3 8B Chat· Stanford HELM specialized suites data docs90%
23o1· Stanford HELM specialized suites data docs90%
24Palmyra X5· Stanford HELM specialized suites data docs90%
25GPT-4.5 Preview· Stanford HELM specialized suites data docs86.7%
26o3 Mini· Stanford HELM specialized suites data docs86.7%
27o4 Mini· Stanford HELM specialized suites data docs86.7%
28Gemini 2.5 Pro Preview 03-25· Stanford HELM specialized suites data docs83.3%
29GPT-4 Turbo· Stanford HELM specialized suites data docs83.3%
30Gemini 2.0 Flash· Stanford HELM specialized suites data docs81.7%
31Gemini 3 Pro Preview· Stanford HELM specialized suites data docs81.7%
32Gemini 2.5 Flash-Lite· Stanford HELM specialized suites data docs80%
33GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs80%
34Llama 3.1 8B Instruct Turbo· Stanford HELM specialized suites data docs80%
35gemini-1.5-flash-002· Stanford HELM specialized suites data docs76.7%
36gemini-2.0-pro-exp-02-05· Stanford HELM specialized suites data docs76.7%
37gemini-2.5-flash-preview-04-17· Stanford HELM specialized suites data docs76.7%
38GPT-4.1 mini· Stanford HELM specialized suites data docs76.7%
39Llama 4 Maverick· Stanford HELM specialized suites data docs76.7%
40GPT-4o mini· Stanford HELM specialized suites data docs75%
41Gemini 2.0 Flash-Lite Preview· Stanford HELM specialized suites data docs73.3%
42GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs73.3%
43GPT-4.1 nano· Stanford HELM specialized suites data docs73.3%
44Qwen2 72B Instruct· Stanford HELM specialized suites data docs73.3%
45Qwen2.5 72B Instruct Turbo· Stanford HELM specialized suites data docs73.3%
46Yi 34B Chat· Stanford HELM specialized suites data docs71.7%
47gemini-1.5-pro-002· Stanford HELM specialized suites data docs70%
48Granite 4.0 H Small· Stanford HELM specialized suites data docs70%
49GPT 4· Stanford HELM specialized suites data docs65%
50Mixtral 8x22B Instruct v0.1· Stanford HELM specialized suites data docs65%

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