Skip to content

Benchmark

HELM AIR-Bench: AIRBench 2024 - #32: Fraud

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
0.98

Score distribution

55.6%
Mean
50.7%
Median
26.5%
Std dev
20%
10th percentile
92%
90th percentile
6.7%
Min
6.7%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.98 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
51Qwen2.5 7B Instruct Turbo· Stanford HELM specialized suites data docs40%
52DeepSeek R1· Stanford HELM specialized suites data docs38.7%
53GLM 4.5 Air· Stanford HELM specialized suites data docs38.7%
54gemini-1.5-flash-002· Stanford HELM specialized suites data docs37.3%
55GPT-4o mini· Stanford HELM specialized suites data docs37.3%
56Grok 3 Mini· Stanford HELM specialized suites data docs34.7%
57O1 Mini· Stanford HELM specialized suites data docs33.3%
58GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs32.7%
59Meta Llama 3.1 70B Instruct Turbo· Stanford HELM specialized suites data docs31.3%
60GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs30.7%
61DeepSeek LLM 67B Chat· Stanford HELM specialized suites data docs30%
62DeepSeek V3· Stanford HELM specialized suites data docs25.3%
63GPT-3.5 Turbosetting not named by the source· Stanford HELM specialized suites data docs25.3%
64Mixtral 8x22B Instruct v0.1· Stanford HELM specialized suites data docs25.3%
65Yi 34B Chat· Stanford HELM specialized suites data docs25.3%
66Grok 4· Stanford HELM specialized suites data docs24%
67Grok 3· Stanford HELM specialized suites data docs21.3%
68Qwen1.5-72B-Chat· Stanford HELM specialized suites data docs20%
69Command R+· Stanford HELM specialized suites data docs18.7%
70Mistral Small· Stanford HELM specialized suites data docs18.7%
71Mistral Large2407· Stanford HELM specialized suites data docs17.3%
72Command R Plus· Stanford HELM specialized suites data docs15.3%
73Mixtral 8x7B Instruct v0.1· Stanford HELM specialized suites data docs12%
74Mistral (7B) Instruct v0.3· Stanford HELM specialized suites data docs9.3%
75DBRX-instruct· Stanford HELM specialized suites data docs6.7%

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