Skip to content

Benchmark

Nejumi 4: ALT_毒性

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
0.97

Score distribution

0.772
Mean
0.804
Median
0.09
Std dev
0.658
10th percentile
0.856
90th percentile
0.363
Min
0.3630.882
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.97 for chat models, measured over 114 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101OpenAI o3openai/o3-2025-04-16: high-effort· Nejumi Leaderboard 4 data docs0.714
102Mistral Large 3 675b Instructmistralai/Mistral-Large-3-675B-Instruct-2512· Nejumi Leaderboard 4 data docs0.711
103Mistral Smallmistral/mistral-small-2503· Nejumi Leaderboard 4 data docs0.708
104Llama 4 Scoutmeta-llama/Llama-4-Scout-17B-16E-Instruct· Nejumi Leaderboard 4 data docs0.706
105Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite· Nejumi Leaderboard 4 data docs0.702
106Gemini 2.5 Flashgoogle/gemini-2.5-flash· Nejumi Leaderboard 4 data docs0.695
107GLM 4.7zai-org/GLM-4.7: reasoning-enabled· Nejumi Leaderboard 4 data docs0.692
108GPT-4.1 miniopenai/gpt-4-1-mini-2025-04-14· Nejumi Leaderboard 4 data docs0.691
109GPT-4.1 nanoopenai/gpt-4-1-nano-2025-04-14· Nejumi Leaderboard 4 data docs0.678
110o1openai/o1-2024-12-17: high-effort· Nejumi Leaderboard 4 data docs0.671
111Qwen3 1.7BQwen/Qwen3-1.7B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.668
112o3 Miniopenai/o3-mini-2025-01-31· Nejumi Leaderboard 4 data docs0.664
113GPT OSS 120Bopenai/gpt-oss-120b: reasoning-enabled· Nejumi Leaderboard 4 data docs0.658
114o4 Miniopenai/o4-mini-2025-04-16· Nejumi Leaderboard 4 data docs0.648
115Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite-preview· Nejumi Leaderboard 4 data docs0.647
116GPT-4o miniopenai/gpt-4o-mini-2024-07-18· Nejumi Leaderboard 4 data docs0.64
117Ministral 3 8Bmistralai/Ministral-3-8B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.629
118Ministral 3 14Bmistralai/Ministral-3-14B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.627
119GLM 4.7 Flashzai-org/GLM-4.7-Flash: reasoning-enabled· Nejumi Leaderboard 4 data docs0.625
120Llama 3.1 405B Instructmeta-llama/Llama-3.1-405B-Instruct-FP8· Nejumi Leaderboard 4 data docs0.609
121Llama 3.3 70B Instructmeta-llama/Llama-3.3-70B-Instruct· Nejumi Leaderboard 4 data docs0.599
122Grok 4.1 Fastx-ai/grok-4-1-fast-reasoning· Nejumi Leaderboard 4 data docs0.593
123Grok 4.20xai/grok-4.20-0309-reasoning· Nejumi Leaderboard 4 data docs0.566
124Ministral 3 3Bmistralai/Ministral-3-3B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.486
125Llama 3.2 3Bmeta-llama/Llama-3.2-3B-Instruct· Nejumi Leaderboard 4 data docs0.405
126Qwen3 0.6BQwen/Qwen3-0.6B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.363

Showing 101–126 of 126 results.

Data credits: Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results