Skip to content

Benchmark

Nejumi 4: GLP_数学的推論

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
2.24

Score distribution

0.864
Mean
0.942
Median
0.149
Std dev
0.622
10th percentile
0.965
90th percentile
0.243
Min
0.2430.982
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.24 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
51Claude Sonnet 4anthropic/claude-sonnet-4-20250514: extended-thinking· Nejumi Leaderboard 4 data docs0.947
52GPT-5.6 Lunaopenai/gpt-5.6-luna: max-effort· Nejumi Leaderboard 4 data docs0.947
53Qwen 3 235B A22BQwen/Qwen3-235B-A22B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.947
54Qwen: Qwen3 VL 8B ThinkingQwen/Qwen3-VL-8B-Thinking· Nejumi Leaderboard 4 data docs0.947
55Claude Haiku 4.5anthropic/claude-haiku-4-5-20251001: extended-thinking· Nejumi Leaderboard 4 data docs0.945
56DeepSeek R1deepseek-ai/DeepSeek-R1-0528: reasoning-enabled· Nejumi Leaderboard 4 data docs0.945
57GPT-5.4 miniopenai/gpt-5.4-mini-2026-03-17: high-effort· Nejumi Leaderboard 4 data docs0.945
58Qwen3 Next 80B A3BQwen/Qwen3-Next-80B-A3B-Thinking: reasoning-enabled· Nejumi Leaderboard 4 data docs0.945
59Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929: extended-thinking· Nejumi Leaderboard 4 data docs0.943
60MiniMax M2.1MiniMaxAI/MiniMax-M2.1: reasoning-enabled· Nejumi Leaderboard 4 data docs0.943
61Qwen3 32BQwen/Qwen3-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.943
62DeepSeek V4 Prodeepseek/deepseek-v4-pro: thinking-max· Nejumi Leaderboard 4 data docs0.942
63GLM 5.2z-ai/glm-5.2: openrouter-reasoning-xhigh· Nejumi Leaderboard 4 data docs0.942
64Grok 4.1 Fastx-ai/grok-4-1-fast-reasoning· Nejumi Leaderboard 4 data docs0.94
65Qwen3 14BQwen/Qwen3-14B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.94
66Qwen3 30B A3BQwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.94
67Qwen3 8BQwen/Qwen3-8B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.94
68Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507· Nejumi Leaderboard 4 data docs0.94
69Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.94
70Claude Opus 4.5anthropic/claude-opus-4.5-20251125: extended-thinking· Nejumi Leaderboard 4 data docs0.935
71Claude Opus 4anthropic/claude-opus-4-20250514: no-thinking· Nejumi Leaderboard 4 data docs0.93
72GPT-5 nanoopenai/gpt-5-nano-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.928
73Qwen3.5 4BQwen/Qwen3.5-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.928
74GLM 4.7 Flashzai-org/GLM-4.7-Flash: reasoning-enabled· Nejumi Leaderboard 4 data docs0.923
75Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: extended-thinking· Nejumi Leaderboard 4 data docs0.922
76Grok 3 Minigrok-3-mini· Nejumi Leaderboard 4 data docs0.922
77Kimi K2 Thinkingmoonshotai/kimi-k2-thinking· Nejumi Leaderboard 4 data docs0.918
78MiniMax M2MiniMaxAI/MiniMax-M2: reasoning-enabled· Nejumi Leaderboard 4 data docs0.913
79Qwen3 4BQwen/Qwen3-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.912
80GPT OSS 120Bopenai/gpt-oss-120b: reasoning-enabled· Nejumi Leaderboard 4 data docs0.908
81Grok 4grok-4· Nejumi Leaderboard 4 data docs0.905
82Qwen3.6 35B A3BQwen/Qwen3.6-35B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.902
83QwQ 32BQwen/QwQ-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.902
84Kimi K2.5moonshotai/Kimi-K2.5: reasoning-enabled· Nejumi Leaderboard 4 data docs0.888
85Qwen3.6 Max Previewqwen/qwen3.6-max-preview: openrouter-reasoning· Nejumi Leaderboard 4 data docs0.885
86Claude Opus 4.5anthropic/claude-opus-4.5-20251125: no-thinking· Nejumi Leaderboard 4 data docs0.872
87Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: no-thinking· Nejumi Leaderboard 4 data docs0.87
88Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite-preview· Nejumi Leaderboard 4 data docs0.87
89Claude Sonnet 4anthropic/claude-sonnet-4-20250514: no-thinking· Nejumi Leaderboard 4 data docs0.865
90Gemini 2.5 Flashgoogle/gemini-2.5-flash· Nejumi Leaderboard 4 data docs0.855
91Qwen3 Max PreviewQwen/Qwen3-Max-Preview· Nejumi Leaderboard 4 data docs0.853
92Grok 3grok-3· Nejumi Leaderboard 4 data docs0.853
93GPT 4.1openai/gpt-4-1-2025-04-14· Nejumi Leaderboard 4 data docs0.85
94Claude 3.5 Sonnetanthropic/claude-3.5-sonnet-20241022· Nejumi Leaderboard 4 data docs0.845
95GPT 5.1openai/gpt-5.1-2025-11-13: none-effort· Nejumi Leaderboard 4 data docs0.842
96Qwen3 1.7BQwen/Qwen3-1.7B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.827
97Gemma 4 E4B-itgoogle/gemma-4-E4B-it· Nejumi Leaderboard 4 data docs0.813
98GPT-4.1 miniopenai/gpt-4-1-mini-2025-04-14· Nejumi Leaderboard 4 data docs0.805
99GPT 4oopenai/gpt-4o-2024-11-20· Nejumi Leaderboard 4 data docs0.803
100DeepSeek V3deepseek-ai/DeepSeek-V3-0324· Nejumi Leaderboard 4 data docs0.8

Showing 51–100 of 126 results.

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