Skip to content

Benchmark

Nejumi 4: 汎用的言語性能(GLP)_AVG

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.79

Score distribution

0.699
Mean
0.721
Median
0.103
Std dev
0.549
10th percentile
0.813
90th percentile
0.346
Min
0.3460.867
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.79 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
101Gemma 4 E2B-itgoogle/gemma-4-E2B-it· Nejumi Leaderboard 4 data docs0.623
102Llama 3.1 405B Instructmeta-llama/Llama-3.1-405B-Instruct-FP8· Nejumi Leaderboard 4 data docs0.622
103Claude 3.5 Sonnetanthropic/claude-3.5-sonnet-20241022· Nejumi Leaderboard 4 data docs0.62
104Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8· Nejumi Leaderboard 4 data docs0.613
105GPT-4o miniopenai/gpt-4o-mini-2024-07-18· Nejumi Leaderboard 4 data docs0.612
106Gemma 3 27B ITgoogle/gemma-3-27b-it· Nejumi Leaderboard 4 data docs0.611
107Llama 3.3 70B Instructmeta-llama/Llama-3.3-70B-Instruct· Nejumi Leaderboard 4 data docs0.595
108Llama 4 Scoutmeta-llama/Llama-4-Scout-17B-16E-Instruct· Nejumi Leaderboard 4 data docs0.58
109GPT-4.1 nanoopenai/gpt-4-1-nano-2025-04-14· Nejumi Leaderboard 4 data docs0.577
110Gemma 3 12B ITgoogle/gemma-3-12b-it· Nejumi Leaderboard 4 data docs0.569
111Ministral 3 14Bmistralai/Ministral-3-14B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.561
112Claude Haiku 3.5anthropic/claude-3.5-haiku-20241022· Nejumi Leaderboard 4 data docs0.549
113Ministral 3 8Bmistralai/Ministral-3-8B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.549
114Mistral Largemistral/mistral-large-2411· Nejumi Leaderboard 4 data docs0.548
115Nova Pro 1.0us.amazon.nova-pro-v1:0· Nejumi Leaderboard 4 data docs0.538
116Qwen3 1.7BQwen/Qwen3-1.7B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.531
117ERNIE 4.5 21B A3Bbaidu/ERNIE-4.5-21B-A3B-Thinking· Nejumi Leaderboard 4 data docs0.53
118Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite· Nejumi Leaderboard 4 data docs0.509
119Nova Lite 1.0us.amazon.nova-lite-v1:0· Nejumi Leaderboard 4 data docs0.508
120Mistral Smallmistral/mistral-small-2503· Nejumi Leaderboard 4 data docs0.503
121Nova Micro 1.0us.amazon.nova-micro-v1:0· Nejumi Leaderboard 4 data docs0.492
122Gemma 3 4B ITgoogle/gemma-3-4b-it· Nejumi Leaderboard 4 data docs0.487
123QwQ 32BQwen/QwQ-32B· Nejumi Leaderboard 4 data docs0.481
124Ministral 3 3Bmistralai/Ministral-3-3B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.421
125Qwen3 0.6BQwen/Qwen3-0.6B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.39
126Llama 3.2 3Bmeta-llama/Llama-3.2-3B-Instruct· Nejumi Leaderboard 4 data docs0.346

Showing 101–126 of 126 results.

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