Skip to content

Benchmark

Nejumi 4: GLP_論理的推論

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.50

Score distribution

0.825
Mean
0.855
Median
0.122
Std dev
0.68
10th percentile
0.935
90th percentile
0.25
Min
0.250.98
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.50 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
51Qwen3 30B A3BQwen/Qwen3-30B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.87
52Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.87
53QwQ 32BQwen/QwQ-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.87
54Claude Opus 4.5anthropic/claude-opus-4.5-20251125: extended-thinking· Nejumi Leaderboard 4 data docs0.865
55Gemini 2.5 Flashgoogle/gemini-2.5-flash· Nejumi Leaderboard 4 data docs0.865
56GPT-5 nanoopenai/gpt-5-nano-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.865
57Qwen3 VL 32B ThinkingQwen/Qwen3-VL-32B-Thinking· Nejumi Leaderboard 4 data docs0.865
58Qwen3.5 122B-A10BQwen/Qwen3.5-122B-A10B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.865
59GPT 5.2openai/gpt-5.2-2025-12-11: xhigh-effort· Nejumi Leaderboard 4 data docs0.86
60MiniMax M2MiniMaxAI/MiniMax-M2: reasoning-enabled· Nejumi Leaderboard 4 data docs0.86
61OpenAI o3openai/o3-2025-04-16: high-effort· Nejumi Leaderboard 4 data docs0.86
62GLM 5.2zai-org/GLM-5.2: reasoning-max· Nejumi Leaderboard 4 data docs0.855
63GPT-5.6 Lunaopenai/gpt-5.6-luna: max-effort· Nejumi Leaderboard 4 data docs0.855
64GPT-5.6 Solopenai/gpt-5.6-sol: max-effort· Nejumi Leaderboard 4 data docs0.855
65Qwen3 32BQwen/Qwen3-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.855
66Qwen3 Max PreviewQwen/Qwen3-Max-Preview· Nejumi Leaderboard 4 data docs0.855
67Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929: extended-thinking· Nejumi Leaderboard 4 data docs0.85
68Claude 3.5 Sonnetanthropic/claude-3.5-sonnet-20241022· Nejumi Leaderboard 4 data docs0.845
69DeepSeek Reasonerdeepseek/DeepSeek-V3.2 (Thinking Mode)· Nejumi Leaderboard 4 data docs0.845
70Gemma 4 E4B-itgoogle/gemma-4-E4B-it· Nejumi Leaderboard 4 data docs0.845
71DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash: reasoning-max· Nejumi Leaderboard 4 data docs0.84
72Qwen 3 235B A22BQwen/Qwen3-235B-A22B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.84
73GPT 5.5openai/gpt-5.5-2026-04-23: xhigh-effort· Nejumi Leaderboard 4 data docs0.835
74Qwen3 4BQwen/Qwen3-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.835
75Qwen3 Next 80B A3BQwen/Qwen3-Next-80B-A3B-Thinking: reasoning-enabled· Nejumi Leaderboard 4 data docs0.835
76Qwen3.5 9BQwen/Qwen3.5-9B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.835
77Qwen3.6 27BQwen/Qwen3.6-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.835
78GLM 4.6zai-org/GLM-4.6-FP8: reasoning-enabled· Nejumi Leaderboard 4 data docs0.83
79GPT 5.1openai/gpt-5.1-2025-11-13: none-effort· Nejumi Leaderboard 4 data docs0.83
80GPT 5.5openai/gpt-5.5-2026-04-23: high-effort· Nejumi Leaderboard 4 data docs0.83
81Qwen3 8BQwen/Qwen3-8B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.83
82GLM 5zai-org/GLM-5: reasoning-enabled· Nejumi Leaderboard 4 data docs0.825
83o4 Miniopenai/o4-mini-2025-04-16· Nejumi Leaderboard 4 data docs0.825
84GPT 5.4openai/gpt-5.4-2026-03-05: xhigh-effort· Nejumi Leaderboard 4 data docs0.82
85Qwen3.6 Max Previewqwen/qwen3.6-max-preview: openrouter-reasoning· Nejumi Leaderboard 4 data docs0.815
86Gemini 2.5 Progoogle/gemini-2.5-pro· Nejumi Leaderboard 4 data docs0.81
87Gemma 4 E2B-itgoogle/gemma-4-E2B-it· Nejumi Leaderboard 4 data docs0.81
88GPT 5openai/gpt-5-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.81
89GPT OSS 120Bopenai/gpt-oss-120b: reasoning-enabled· Nejumi Leaderboard 4 data docs0.81
90Llama 3.1 405B Instructmeta-llama/Llama-3.1-405B-Instruct-FP8· Nejumi Leaderboard 4 data docs0.81
91Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8· Nejumi Leaderboard 4 data docs0.81
92GPT-5.4 miniopenai/gpt-5.4-mini-2026-03-17: high-effort· Nejumi Leaderboard 4 data docs0.805
93GPT 4.1openai/gpt-4-1-2025-04-14· Nejumi Leaderboard 4 data docs0.795
94GPT 5.4openai/gpt-5.4-2026-03-05: high-effort· Nejumi Leaderboard 4 data docs0.795
95Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite-preview· Nejumi Leaderboard 4 data docs0.79
96o1openai/o1-2024-12-17: high-effort· Nejumi Leaderboard 4 data docs0.79
97Qwen: Qwen3 VL 8B ThinkingQwen/Qwen3-VL-8B-Thinking· Nejumi Leaderboard 4 data docs0.79
98Kimi K2 Thinkingmoonshotai/kimi-k2-thinking· Nejumi Leaderboard 4 data docs0.785
99Nova Pro 1.0us.amazon.nova-pro-v1:0· Nejumi Leaderboard 4 data docs0.775
100Qwen3 30B A3BQwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.775

Showing 51–100 of 126 results.

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