Skip to content

Benchmark

Nejumi 4: ALT_制御性

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.41

Score distribution

0.825
Mean
0.855
Median
0.098
Std dev
0.67
10th percentile
0.923
90th percentile
0.517
Min
0.5170.947
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.41 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
51Grok 4grok-4· Nejumi Leaderboard 4 data docs0.872
52Qwen3.6 27BQwen/Qwen3.6-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.87
53Qwen3.5 122B-A10BQwen/Qwen3.5-122B-A10B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.868
54Grok 3grok-3· Nejumi Leaderboard 4 data docs0.868
55Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.868
56Qwen3.5 27BQwen/Qwen3.5-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.868
57GPT-5 nanoopenai/gpt-5-nano-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.868
58Gemini 3 Pro Previewgoogle/gemini-3-pro-preview· Nejumi Leaderboard 4 data docs0.866
59Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929: extended-thinking· Nejumi Leaderboard 4 data docs0.865
60Grok 4.1 Fastx-ai/grok-4-1-fast-reasoning· Nejumi Leaderboard 4 data docs0.862
61GLM 4.7zai-org/GLM-4.7: reasoning-enabled· Nejumi Leaderboard 4 data docs0.862
62Kimi K2 Thinkingmoonshotai/kimi-k2-thinking· Nejumi Leaderboard 4 data docs0.856
63Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: extended-thinking· Nejumi Leaderboard 4 data docs0.855
64Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507· Nejumi Leaderboard 4 data docs0.855
65Qwen3 VL 32B ThinkingQwen/Qwen3-VL-32B-Thinking· Nejumi Leaderboard 4 data docs0.855
66DeepSeek Reasonerdeepseek/DeepSeek-V3.2 (Thinking Mode)· Nejumi Leaderboard 4 data docs0.854
67Qwen3.5 35B A3BQwen/Qwen3.5-35B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.852
68Gemini 2.5 Progoogle/gemini-2.5-pro· Nejumi Leaderboard 4 data docs0.852
69DeepSeek V3.2deepseek-ai/DeepSeek-V3.2: reasoning-enabled· Nejumi Leaderboard 4 data docs0.851
70GPT OSS 120Bopenai/gpt-oss-120b: reasoning-enabled· Nejumi Leaderboard 4 data docs0.851
71Claude Haiku 4.5anthropic/claude-haiku-4-5-20251001: extended-thinking· Nejumi Leaderboard 4 data docs0.848
72MiniMax M3MiniMaxAI/MiniMax-M3: reasoning-enabled· Nejumi Leaderboard 4 data docs0.846
73GPT-4.1 miniopenai/gpt-4-1-mini-2025-04-14· Nejumi Leaderboard 4 data docs0.841
74Grok 3 Minigrok-3-mini· Nejumi Leaderboard 4 data docs0.832
75GPT-4o miniopenai/gpt-4o-mini-2024-07-18· Nejumi Leaderboard 4 data docs0.829
76GPT 4oopenai/gpt-4o-2024-11-20· Nejumi Leaderboard 4 data docs0.825
77Qwen3 Next 80B A3B InstructQwen/Qwen3-Next-80B-A3B-Instruct· Nejumi Leaderboard 4 data docs0.824
78Qwen: Qwen3 VL 8B ThinkingQwen/Qwen3-VL-8B-Thinking· Nejumi Leaderboard 4 data docs0.812
79Gemini 2.5 Flashgoogle/gemini-2.5-flash· Nejumi Leaderboard 4 data docs0.812
80Qwen3.5 9BQwen/Qwen3.5-9B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.811
81Qwen3 32BQwen/Qwen3-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.81
82Qwen3 14BQwen/Qwen3-14B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.81
83Gemma 4 E2B-itgoogle/gemma-4-E2B-it· Nejumi Leaderboard 4 data docs0.808
84DeepSeek V3deepseek-ai/DeepSeek-V3-0324· Nejumi Leaderboard 4 data docs0.807
85Qwen 3 235B A22BQwen/Qwen3-235B-A22B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.807
86GPT-4.1 nanoopenai/gpt-4-1-nano-2025-04-14· Nejumi Leaderboard 4 data docs0.804
87Gemma 4 E4B-itgoogle/gemma-4-E4B-it· Nejumi Leaderboard 4 data docs0.803
88Gemma 3 12B ITgoogle/gemma-3-12b-it· Nejumi Leaderboard 4 data docs0.803
89Mistral Large 3 675b Instructmistralai/Mistral-Large-3-675B-Instruct-2512· Nejumi Leaderboard 4 data docs0.796
90Qwen3 30B A3BQwen/Qwen3-30B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.792
91Llama 3.3 70B Instructmeta-llama/Llama-3.3-70B-Instruct· Nejumi Leaderboard 4 data docs0.79
92Qwen3 8BQwen/Qwen3-8B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.787
93Gemma 3 27B ITgoogle/gemma-3-27b-it· Nejumi Leaderboard 4 data docs0.786
94GLM 4.7 Flashzai-org/GLM-4.7-Flash: reasoning-enabled· Nejumi Leaderboard 4 data docs0.786
95MiniMax M2.1MiniMaxAI/MiniMax-M2.1: reasoning-enabled· Nejumi Leaderboard 4 data docs0.774
96Qwen3.5 4BQwen/Qwen3.5-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.773
97Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8· Nejumi Leaderboard 4 data docs0.769
98DeepSeek R1deepseek-ai/DeepSeek-R1-0528: reasoning-enabled· Nejumi Leaderboard 4 data docs0.768
99Mistral Smallmistral/mistral-small-2503· Nejumi Leaderboard 4 data docs0.766
100QwQ 32BQwen/QwQ-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.763

Showing 51–100 of 126 results.

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