Skip to content

Benchmark

Nejumi 4: GLP_応用的言語性能

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.76

Score distribution

0.857
Mean
0.877
Median
0.058
Std dev
0.796
10th percentile
0.898
90th percentile
0.507
Min
0.5070.91
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.76 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
101Nova Lite 1.0us.amazon.nova-lite-v1:0· Nejumi Leaderboard 4 data docs0.839
102Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8· Nejumi Leaderboard 4 data docs0.839
103Nova Pro 1.0us.amazon.nova-pro-v1:0· Nejumi Leaderboard 4 data docs0.837
104Gemma 3 27B ITgoogle/gemma-3-27b-it· Nejumi Leaderboard 4 data docs0.827
105Llama 4 Scoutmeta-llama/Llama-4-Scout-17B-16E-Instruct· Nejumi Leaderboard 4 data docs0.827
106Llama 3.1 405B Instructmeta-llama/Llama-3.1-405B-Instruct-FP8· Nejumi Leaderboard 4 data docs0.82
107Ministral 3 14Bmistralai/Ministral-3-14B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.82
108Mistral Largemistral/mistral-large-2411· Nejumi Leaderboard 4 data docs0.815
109Nova Micro 1.0us.amazon.nova-micro-v1:0· Nejumi Leaderboard 4 data docs0.814
110Qwen3 4BQwen/Qwen3-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.812
111Gemma 3 12B ITgoogle/gemma-3-12b-it· Nejumi Leaderboard 4 data docs0.81
112Llama 3.3 70B Instructmeta-llama/Llama-3.3-70B-Instruct· Nejumi Leaderboard 4 data docs0.806
113Ministral 3 8Bmistralai/Ministral-3-8B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.796
114Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507· Nejumi Leaderboard 4 data docs0.792
115Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.792
116Gemini 2.5 Flashgoogle/gemini-2.5-flash· Nejumi Leaderboard 4 data docs0.776
117Gemma 3 4B ITgoogle/gemma-3-4b-it· Nejumi Leaderboard 4 data docs0.776
118ERNIE 4.5 21B A3Bbaidu/ERNIE-4.5-21B-A3B-Thinking· Nejumi Leaderboard 4 data docs0.773
119Kimi K2 Thinkingmoonshotai/kimi-k2-thinking· Nejumi Leaderboard 4 data docs0.76
120Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite· Nejumi Leaderboard 4 data docs0.748
121Mistral Smallmistral/mistral-small-2503· Nejumi Leaderboard 4 data docs0.715
122Qwen3 1.7BQwen/Qwen3-1.7B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.714
123Ministral 3 3Bmistralai/Ministral-3-3B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.685
124QwQ 32BQwen/QwQ-32B· Nejumi Leaderboard 4 data docs0.685
125Llama 3.2 3Bmeta-llama/Llama-3.2-3B-Instruct· Nejumi Leaderboard 4 data docs0.627
126Qwen3 0.6BQwen/Qwen3-0.6B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.507

Showing 101–126 of 126 results.

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