Skip to content

Benchmark

Nejumi 4: GLP_抽象的推論

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.27

Score distribution

0.331
Mean
0.26
Median
0.284
Std dev
0.04
10th percentile
0.83
90th percentile
0.01
Min
0.010.98
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.27 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
101Qwen3 14BQwen/Qwen3-14B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.08
102Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite-preview· Nejumi Leaderboard 4 data docs0.07
103GLM 4.7 Flashzai-org/GLM-4.7-Flash: reasoning-enabled· Nejumi Leaderboard 4 data docs0.07
104GPT 4oopenai/gpt-4o-2024-11-20· Nejumi Leaderboard 4 data docs0.07
105Qwen3 8BQwen/Qwen3-8B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.07
106Gemma 4 E4B-itgoogle/gemma-4-E4B-it· Nejumi Leaderboard 4 data docs0.06
107QwQ 32BQwen/QwQ-32B· Nejumi Leaderboard 4 data docs0.06
108Gemma 3 12B ITgoogle/gemma-3-12b-it· Nejumi Leaderboard 4 data docs0.05
109Gemma 3 27B ITgoogle/gemma-3-27b-it· Nejumi Leaderboard 4 data docs0.05
110Mistral Largemistral/mistral-large-2411· Nejumi Leaderboard 4 data docs0.05
111Nova Lite 1.0us.amazon.nova-lite-v1:0· Nejumi Leaderboard 4 data docs0.05
112Qwen3 4BQwen/Qwen3-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.05
113Gemma 4 E2B-itgoogle/gemma-4-E2B-it· Nejumi Leaderboard 4 data docs0.04
114GPT-4o miniopenai/gpt-4o-mini-2024-07-18· Nejumi Leaderboard 4 data docs0.04
115Llama 3.2 3Bmeta-llama/Llama-3.2-3B-Instruct· Nejumi Leaderboard 4 data docs0.04
116Ministral 3 8Bmistralai/Ministral-3-8B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.04
117Qwen3 1.7BQwen/Qwen3-1.7B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.04
118Qwen3 30B A3BQwen/Qwen3-30B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.04
119ERNIE 4.5 21B A3Bbaidu/ERNIE-4.5-21B-A3B-Thinking· Nejumi Leaderboard 4 data docs0.03
120Gemma 3 4B ITgoogle/gemma-3-4b-it· Nejumi Leaderboard 4 data docs0.02
121GPT-4.1 nanoopenai/gpt-4-1-nano-2025-04-14· Nejumi Leaderboard 4 data docs0.02
122Llama 4 Scoutmeta-llama/Llama-4-Scout-17B-16E-Instruct· Nejumi Leaderboard 4 data docs0.02
123Ministral 3 3Bmistralai/Ministral-3-3B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.02
124Nova Pro 1.0us.amazon.nova-pro-v1:0· Nejumi Leaderboard 4 data docs0.02
125Qwen3 0.6BQwen/Qwen3-0.6B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.02
126Nova Micro 1.0us.amazon.nova-micro-v1:0· Nejumi Leaderboard 4 data docs0.01

Showing 101–126 of 126 results.

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