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
1Claude Opus 5anthropic/claude-opus-5: adaptive-thinking-max· Nejumi Leaderboard 4 data docs0.867
2Claude Fable 5anthropic/claude-fable-5: adaptive-thinking-max with fallback to Opus 4.8· Nejumi Leaderboard 4 data docs0.85
3GPT-5.6 Solopenai/gpt-5.6-sol: max-effort· Nejumi Leaderboard 4 data docs0.84
4GPT-5.6 Terraopenai/gpt-5.6-terra: max-effort· Nejumi Leaderboard 4 data docs0.836
5Claude Opus 4.8anthropic/claude-opus-4.8: adaptive-thinking-xhigh· Nejumi Leaderboard 4 data docs0.833
6GPT 5.5openai/gpt-5.5-2026-04-23: high-effort· Nejumi Leaderboard 4 data docs0.831
7GPT 5.5openai/gpt-5.5-2026-04-23: xhigh-effort· Nejumi Leaderboard 4 data docs0.83
8Claude Opus 4.7anthropic/claude-opus-4.7: adaptive-thinking-xhigh· Nejumi Leaderboard 4 data docs0.83
9Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview· Nejumi Leaderboard 4 data docs0.828
10Gemini 3.6 Flashgoogle/gemini-3.6-flash· Nejumi Leaderboard 4 data docs0.825
11Kimi K3moonshotai/kimi-k3: reasoning-max· Nejumi Leaderboard 4 data docs0.82
12Gemini 3.5 Flashgoogle/gemini-3.5-flash· Nejumi Leaderboard 4 data docs0.815
13Claude Opus 4.6anthropic/claude-opus-4-6: extended-thinking· Nejumi Leaderboard 4 data docs0.813
14GPT 5.4openai/gpt-5.4-2026-03-05: high-effort· Nejumi Leaderboard 4 data docs0.811
15Gemini 3 Flashgoogle/gemini-3-flash-preview· Nejumi Leaderboard 4 data docs0.811
16GPT 5.4openai/gpt-5.4-2026-03-05: xhigh-effort· Nejumi Leaderboard 4 data docs0.809
17GPT-5.6 Lunaopenai/gpt-5.6-luna: max-effort· Nejumi Leaderboard 4 data docs0.809
18Grok 4.5xai/grok-4.5: reasoning-high· Nejumi Leaderboard 4 data docs0.804
19Gemini 3 Pro Previewgoogle/gemini-3-pro-preview· Nejumi Leaderboard 4 data docs0.799
20GPT 5.2openai/gpt-5.2-2025-12-11: xhigh-effort· Nejumi Leaderboard 4 data docs0.797
21Claude Sonnet 4.6anthropic/claude-sonnet-4.6: extended-thinking· Nejumi Leaderboard 4 data docs0.796
22Grok 4.20xai/grok-4.20-0309-reasoning· Nejumi Leaderboard 4 data docs0.794
23MiniMax M3MiniMaxAI/MiniMax-M3: reasoning-enabled· Nejumi Leaderboard 4 data docs0.79
24Qwen3.6 Max Previewqwen/qwen3.6-max-preview: openrouter-reasoning· Nejumi Leaderboard 4 data docs0.786
25GLM 5.2zai-org/GLM-5.2: reasoning-max· Nejumi Leaderboard 4 data docs0.786
26Gemma 4 31B ITgoogle/gemma-4-31b-it· Nejumi Leaderboard 4 data docs0.785
27DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro: reasoning-max· Nejumi Leaderboard 4 data docs0.784
28DeepSeek V4 Prodeepseek/deepseek-v4-pro: thinking-max· Nejumi Leaderboard 4 data docs0.78
29GLM 5.2z-ai/glm-5.2: openrouter-reasoning-xhigh· Nejumi Leaderboard 4 data docs0.778
30Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.776
31Claude Opus 4.5anthropic/claude-opus-4.5-20251125: extended-thinking· Nejumi Leaderboard 4 data docs0.773
32DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash: reasoning-max· Nejumi Leaderboard 4 data docs0.772
33GLM 5zai-org/GLM-5: reasoning-enabled· Nejumi Leaderboard 4 data docs0.771
34GPT 5.1openai/gpt-5.1-2025-11-13: high-effort· Nejumi Leaderboard 4 data docs0.771
35GLM 4.7zai-org/GLM-4.7: reasoning-enabled· Nejumi Leaderboard 4 data docs0.766
36OpenAI o3openai/o3-2025-04-16: high-effort· Nejumi Leaderboard 4 data docs0.764
37Qwen3.5 27BQwen/Qwen3.5-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.761
38Qwen3.5 122B-A10BQwen/Qwen3.5-122B-A10B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.761
39Qwen3.6 27BQwen/Qwen3.6-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.761
40GPT 5openai/gpt-5-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.759
41Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it· Nejumi Leaderboard 4 data docs0.758
42GPT-5.4 miniopenai/gpt-5.4-mini-2026-03-17: high-effort· Nejumi Leaderboard 4 data docs0.758
43o4 Miniopenai/o4-mini-2025-04-16· Nejumi Leaderboard 4 data docs0.756
44Gemini 2.5 Progoogle/gemini-2.5-pro· Nejumi Leaderboard 4 data docs0.755
45Kimi K2.5moonshotai/Kimi-K2.5: reasoning-enabled· Nejumi Leaderboard 4 data docs0.754
46Grok 4.1 Fastx-ai/grok-4-1-fast-reasoning· Nejumi Leaderboard 4 data docs0.753
47Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929: extended-thinking· Nejumi Leaderboard 4 data docs0.751
48Claude Opus 4.1anthropic/claude-opus-4-1-20250805: extended-thinking· Nejumi Leaderboard 4 data docs0.75
49Grok 4grok-4· Nejumi Leaderboard 4 data docs0.748
50DeepSeek V3.2deepseek-ai/DeepSeek-V3.2: reasoning-enabled· Nejumi Leaderboard 4 data docs0.747

Showing 1–50 of 126 results.

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