Skip to content

Benchmark

Nejumi 4: GLP_一般的知識

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.56

Score distribution

0.69
Mean
0.729
Median
0.14
Std dev
0.512
10th percentile
0.83
90th percentile
0.214
Min
0.2140.856
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.56 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
101Claude Sonnet 4anthropic/claude-sonnet-4-20250514: no-thinking· Nejumi Leaderboard 4 data docs0.579
102Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: no-thinking· Nejumi Leaderboard 4 data docs0.576
103GPT-4.1 nanoopenai/gpt-4-1-nano-2025-04-14· Nejumi Leaderboard 4 data docs0.575
104Qwen3 30B A3BQwen/Qwen3-30B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.572
105Qwen: Qwen3 VL 8B ThinkingQwen/Qwen3-VL-8B-Thinking· Nejumi Leaderboard 4 data docs0.57
106Ministral 3 14Bmistralai/Ministral-3-14B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.557
107Gemma 4 E2B-itgoogle/gemma-4-E2B-it· Nejumi Leaderboard 4 data docs0.547
108Claude 3.5 Sonnetanthropic/claude-3.5-sonnet-20241022· Nejumi Leaderboard 4 data docs0.544
109Qwen3 8BQwen/Qwen3-8B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.527
110QwQ 32BQwen/QwQ-32B· Nejumi Leaderboard 4 data docs0.526
111Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507· Nejumi Leaderboard 4 data docs0.525
112Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.525
113Mistral Smallmistral/mistral-small-2503· Nejumi Leaderboard 4 data docs0.512
114Ministral 3 8Bmistralai/Ministral-3-8B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.492
115Gemma 3 4B ITgoogle/gemma-3-4b-it· Nejumi Leaderboard 4 data docs0.489
116Claude Haiku 3.5anthropic/claude-3.5-haiku-20241022· Nejumi Leaderboard 4 data docs0.471
117Mistral Largemistral/mistral-large-2411· Nejumi Leaderboard 4 data docs0.469
118Qwen3 4BQwen/Qwen3-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.455
119Nova Pro 1.0us.amazon.nova-pro-v1:0· Nejumi Leaderboard 4 data docs0.452
120ERNIE 4.5 21B A3Bbaidu/ERNIE-4.5-21B-A3B-Thinking· Nejumi Leaderboard 4 data docs0.411
121Nova Lite 1.0us.amazon.nova-lite-v1:0· Nejumi Leaderboard 4 data docs0.383
122Qwen3 1.7BQwen/Qwen3-1.7B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.357
123Ministral 3 3Bmistralai/Ministral-3-3B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.344
124Nova Micro 1.0us.amazon.nova-micro-v1:0· Nejumi Leaderboard 4 data docs0.317
125Llama 3.2 3Bmeta-llama/Llama-3.2-3B-Instruct· Nejumi Leaderboard 4 data docs0.25
126Qwen3 0.6BQwen/Qwen3-0.6B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.214

Showing 101–126 of 126 results.

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