Skip to content

Benchmark

Nejumi 4: GLP_基礎的言語性能

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.88

Score distribution

0.768
Mean
0.809
Median
0.111
Std dev
0.597
10th percentile
0.861
90th percentile
0.409
Min
0.4090.878
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.88 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
101Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507· Nejumi Leaderboard 4 data docs0.714
102Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.714
103Qwen: Qwen3 VL 8B ThinkingQwen/Qwen3-VL-8B-Thinking· Nejumi Leaderboard 4 data docs0.711
104Mistral Smallmistral/mistral-small-2503· Nejumi Leaderboard 4 data docs0.703
105Gemma 4 E2B-itgoogle/gemma-4-E2B-it· Nejumi Leaderboard 4 data docs0.696
106Gemma 3 12B ITgoogle/gemma-3-12b-it· Nejumi Leaderboard 4 data docs0.683
107GPT-4.1 nanoopenai/gpt-4-1-nano-2025-04-14· Nejumi Leaderboard 4 data docs0.671
108Qwen3 1.7BQwen/Qwen3-1.7B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.656
109Ministral 3 8Bmistralai/Ministral-3-8B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.651
110Ministral 3 14Bmistralai/Ministral-3-14B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.63
111Qwen3 0.6BQwen/Qwen3-0.6B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.625
112ERNIE 4.5 21B A3Bbaidu/ERNIE-4.5-21B-A3B-Thinking· Nejumi Leaderboard 4 data docs0.624
113Gemma 3 4B ITgoogle/gemma-3-4b-it· Nejumi Leaderboard 4 data docs0.597
114Claude Opus 4.5anthropic/claude-opus-4.5-20251125: no-thinking· Nejumi Leaderboard 4 data docs0.566
115Claude Sonnet 4anthropic/claude-sonnet-4-20250514: no-thinking· Nejumi Leaderboard 4 data docs0.564
116Gemini 2.5 Flash-Litegoogle/gemini-2.5-flash-lite· Nejumi Leaderboard 4 data docs0.553
117Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: no-thinking· Nejumi Leaderboard 4 data docs0.547
118Claude 3.5 Sonnetanthropic/claude-3.5-sonnet-20241022· Nejumi Leaderboard 4 data docs0.542
119Mistral Largemistral/mistral-large-2411· Nejumi Leaderboard 4 data docs0.526
120Nova Pro 1.0us.amazon.nova-pro-v1:0· Nejumi Leaderboard 4 data docs0.489
121Claude Haiku 3.5anthropic/claude-3.5-haiku-20241022· Nejumi Leaderboard 4 data docs0.472
122Nova Lite 1.0us.amazon.nova-lite-v1:0· Nejumi Leaderboard 4 data docs0.456
123Ministral 3 3Bmistralai/Ministral-3-3B-Reasoning-2512· Nejumi Leaderboard 4 data docs0.449
124Nova Micro 1.0us.amazon.nova-micro-v1:0· Nejumi Leaderboard 4 data docs0.443
125Llama 3.2 3Bmeta-llama/Llama-3.2-3B-Instruct· Nejumi Leaderboard 4 data docs0.425
126QwQ 32BQwen/QwQ-32B· Nejumi Leaderboard 4 data docs0.409

Showing 101–126 of 126 results.

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