Skip to content

Benchmark

Nejumi 4: AVG_jaster_0shot

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
2.02

Score distribution

0.754
Mean
0.796
Median
0.122
Std dev
0.547
10th percentile
0.861
90th percentile
0.317
Min
0.3170.88
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.02 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 Opus 4.1anthropic/claude-opus-4-1-20250805: extended-thinking· Nejumi Leaderboard 4 data docs0.821
52Qwen3.5 27BQwen/Qwen3.5-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.819
53Qwen3.5 35B A3BQwen/Qwen3.5-35B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.819
54Qwen3.6 27BQwen/Qwen3.6-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.819
55Grok 4.1 Fastx-ai/grok-4-1-fast-reasoning· Nejumi Leaderboard 4 data docs0.815
56Qwen3.6 35B A3BQwen/Qwen3.6-35B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.808
57Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929: extended-thinking· Nejumi Leaderboard 4 data docs0.808
58Grok 3 Minigrok-3-mini· Nejumi Leaderboard 4 data docs0.805
59o3 Miniopenai/o3-mini-2025-01-31· Nejumi Leaderboard 4 data docs0.805
60Kimi K2 Thinkingmoonshotai/kimi-k2-thinking· Nejumi Leaderboard 4 data docs0.803
61Claude Sonnet 4anthropic/claude-sonnet-4-20250514: extended-thinking· Nejumi Leaderboard 4 data docs0.798
62MiniMax M2.1MiniMaxAI/MiniMax-M2.1: reasoning-enabled· Nejumi Leaderboard 4 data docs0.798
63Claude Haiku 4.5anthropic/claude-haiku-4-5-20251001: extended-thinking· Nejumi Leaderboard 4 data docs0.796
64GPT-5 nanoopenai/gpt-5-nano-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.792
65Qwen 3 235B A22B Thinking 2507Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.792
66GPT OSS 120Bopenai/gpt-oss-120b: reasoning-enabled· Nejumi Leaderboard 4 data docs0.791
67Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite-preview· Nejumi Leaderboard 4 data docs0.791
68Claude Opus 4anthropic/claude-opus-4-20250514: no-thinking· Nejumi Leaderboard 4 data docs0.789
69GPT 4.1openai/gpt-4-1-2025-04-14· Nejumi Leaderboard 4 data docs0.783
70Qwen3.5 9BQwen/Qwen3.5-9B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.782
71Qwen3 Next 80B A3BQwen/Qwen3-Next-80B-A3B-Thinking· Nejumi Leaderboard 4 data docs0.78
72GPT 5.1openai/gpt-5.1-2025-11-13: none-effort· Nejumi Leaderboard 4 data docs0.777
73Qwen3 Next 80B A3BQwen/Qwen3-Next-80B-A3B-Thinking: reasoning-enabled· Nejumi Leaderboard 4 data docs0.777
74Qwen3 Max PreviewQwen/Qwen3-Max-Preview· Nejumi Leaderboard 4 data docs0.77
75GLM 4.7 Flashzai-org/GLM-4.7-Flash: reasoning-enabled· Nejumi Leaderboard 4 data docs0.767
76MiniMax M2MiniMaxAI/MiniMax-M2: reasoning-enabled· Nejumi Leaderboard 4 data docs0.767
77Qwen3 VL 32B ThinkingQwen/Qwen3-VL-32B-Thinking· Nejumi Leaderboard 4 data docs0.766
78Gemini 2.5 Flashgoogle/gemini-2.5-flash· Nejumi Leaderboard 4 data docs0.766
79Grok 3grok-3· Nejumi Leaderboard 4 data docs0.765
80GPT 4oopenai/gpt-4o-2024-11-20· Nejumi Leaderboard 4 data docs0.765
81Qwen 3 235B A22BQwen/Qwen3-235B-A22B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.765
82Qwen3 32BQwen/Qwen3-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.76
83QwQ 32BQwen/QwQ-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.759
84Qwen3 30B A3BQwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.758
85Qwen3.5 4BQwen/Qwen3.5-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.752
86Qwen3 14BQwen/Qwen3-14B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.748
87Qwen3 30B A3BQwen/Qwen3-30B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.747
88GPT-4.1 miniopenai/gpt-4-1-mini-2025-04-14· Nejumi Leaderboard 4 data docs0.737
89Gemma 4 E4B-itgoogle/gemma-4-E4B-it· Nejumi Leaderboard 4 data docs0.736
90Qwen: Qwen3 VL 8B ThinkingQwen/Qwen3-VL-8B-Thinking· Nejumi Leaderboard 4 data docs0.726
91Qwen3 Next 80B A3B InstructQwen/Qwen3-Next-80B-A3B-Instruct· Nejumi Leaderboard 4 data docs0.723
92Qwen3 8BQwen/Qwen3-8B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.722
93DeepSeek V3deepseek-ai/DeepSeek-V3-0324· Nejumi Leaderboard 4 data docs0.717
94Gemma 4 E2B-itgoogle/gemma-4-E2B-it· Nejumi Leaderboard 4 data docs0.711
95Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507· Nejumi Leaderboard 4 data docs0.707
96Qwen3-4B-Thinking-2507Qwen/Qwen3-4B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.707
97Mistral Large 3 675b Instructmistralai/Mistral-Large-3-675B-Instruct-2512· Nejumi Leaderboard 4 data docs0.702
98Llama 3.1 405B Instructmeta-llama/Llama-3.1-405B-Instruct-FP8· Nejumi Leaderboard 4 data docs0.702
99Qwen3 4BQwen/Qwen3-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.691
100GPT-4o miniopenai/gpt-4o-mini-2024-07-18· Nejumi Leaderboard 4 data docs0.685

Showing 51–100 of 126 results.

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