Skip to content

Benchmark

Nejumi 4: GLP_アプリケーション開発

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.44

Score distribution

0.579
Mean
0.6
Median
0.088
Std dev
0.476
10th percentile
0.67
90th percentile
0.264
Min
0.2640.804
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.44 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
51o3 Miniopenai/o3-mini-2025-01-31· Nejumi Leaderboard 4 data docs0.609
52Qwen3 Next 80B A3BQwen/Qwen3-Next-80B-A3B-Thinking: reasoning-enabled· Nejumi Leaderboard 4 data docs0.608
53Grok 4.5xai/grok-4.5: reasoning-high· Nejumi Leaderboard 4 data docs0.608
54GPT 4oopenai/gpt-4o-2024-11-20· Nejumi Leaderboard 4 data docs0.608
55Qwen3 Max PreviewQwen/Qwen3-Max-Preview· Nejumi Leaderboard 4 data docs0.607
56o1openai/o1-2024-12-17: high-effort· Nejumi Leaderboard 4 data docs0.606
57DeepSeek R1deepseek-ai/DeepSeek-R1-0528: reasoning-enabled· Nejumi Leaderboard 4 data docs0.605
58DeepSeek V4 Prodeepseek/deepseek-v4-pro: thinking-max· Nejumi Leaderboard 4 data docs0.604
59Claude 3.5 Sonnetanthropic/claude-3.5-sonnet-20241022· Nejumi Leaderboard 4 data docs0.603
60GPT 5.2openai/gpt-5.2-2025-12-11: xhigh-effort· Nejumi Leaderboard 4 data docs0.603
61DeepSeek Reasonerdeepseek/DeepSeek-V3.2 (Thinking Mode)· Nejumi Leaderboard 4 data docs0.602
62Qwen3 Next 80B A3BQwen/Qwen3-Next-80B-A3B-Thinking· Nejumi Leaderboard 4 data docs0.602
63Gemini 2.5 Progoogle/gemini-2.5-pro· Nejumi Leaderboard 4 data docs0.6
64GPT 5.1openai/gpt-5.1-2025-11-13: high-effort· Nejumi Leaderboard 4 data docs0.598
65Grok 3grok-3· Nejumi Leaderboard 4 data docs0.598
66GPT 5openai/gpt-5-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.594
67GPT 4.1openai/gpt-4-1-2025-04-14· Nejumi Leaderboard 4 data docs0.594
68Qwen3.5 35B A3BQwen/Qwen3.5-35B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.592
69GPT-5.4 miniopenai/gpt-5.4-mini-2026-03-17: high-effort· Nejumi Leaderboard 4 data docs0.591
70Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: no-thinking· Nejumi Leaderboard 4 data docs0.591
71Qwen3 Next 80B A3B InstructQwen/Qwen3-Next-80B-A3B-Instruct· Nejumi Leaderboard 4 data docs0.59
72DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash: reasoning-max· Nejumi Leaderboard 4 data docs0.587
73GPT-4.1 miniopenai/gpt-4-1-mini-2025-04-14· Nejumi Leaderboard 4 data docs0.587
74GPT 5.4openai/gpt-5.4-2026-03-05: xhigh-effort· Nejumi Leaderboard 4 data docs0.585
75Grok 4grok-4· Nejumi Leaderboard 4 data docs0.578
76Qwen3 30B A3BQwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.568
77Gemma 4 E4B-itgoogle/gemma-4-E4B-it· Nejumi Leaderboard 4 data docs0.568
78Gemini 2.5 Flashgoogle/gemini-2.5-flash· Nejumi Leaderboard 4 data docs0.56
79Nova Pro 1.0us.amazon.nova-pro-v1:0· Nejumi Leaderboard 4 data docs0.56
80Qwen3 VL 32B ThinkingQwen/Qwen3-VL-32B-Thinking· Nejumi Leaderboard 4 data docs0.559
81GPT OSS 120Bopenai/gpt-oss-120b: reasoning-enabled· Nejumi Leaderboard 4 data docs0.558
82Qwen3 14BQwen/Qwen3-14B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.557
83GPT 5.1openai/gpt-5.1-2025-11-13: none-effort· Nejumi Leaderboard 4 data docs0.556
84GLM 4.7 Flashzai-org/GLM-4.7-Flash: reasoning-enabled· Nejumi Leaderboard 4 data docs0.554
85MiniMax M2.1MiniMaxAI/MiniMax-M2.1: reasoning-enabled· Nejumi Leaderboard 4 data docs0.552
86Qwen 3 235B A22BQwen/Qwen3-235B-A22B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.548
87MiniMax M2MiniMaxAI/MiniMax-M2: reasoning-enabled· Nejumi Leaderboard 4 data docs0.545
88Qwen: Qwen3 VL 8B ThinkingQwen/Qwen3-VL-8B-Thinking· Nejumi Leaderboard 4 data docs0.541
89QwQ 32BQwen/QwQ-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.541
90Mistral Large 3 675b Instructmistralai/Mistral-Large-3-675B-Instruct-2512· Nejumi Leaderboard 4 data docs0.541
91Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507· Nejumi Leaderboard 4 data docs0.538
92Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.538
93GPT-4o miniopenai/gpt-4o-mini-2024-07-18· Nejumi Leaderboard 4 data docs0.537
94Qwen3 32BQwen/Qwen3-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.533
95DeepSeek V3deepseek-ai/DeepSeek-V3-0324· Nejumi Leaderboard 4 data docs0.532
96Claude Haiku 3.5anthropic/claude-3.5-haiku-20241022· Nejumi Leaderboard 4 data docs0.528
97Grok 3 Minigrok-3-mini· Nejumi Leaderboard 4 data docs0.525
98Qwen3 8BQwen/Qwen3-8B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.524
99Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8· Nejumi Leaderboard 4 data docs0.52
100Gemma 4 E2B-itgoogle/gemma-4-E2B-it· Nejumi Leaderboard 4 data docs0.52

Showing 51–100 of 126 results.

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