Skip to content

Benchmark

Nejumi 4: GLP_情報検索

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.49

Score distribution

0.754
Mean
0.768
Median
0.06
Std dev
0.701
10th percentile
0.808
90th percentile
0.374
Min
0.3740.825
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.49 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
51DeepSeek R1deepseek-ai/DeepSeek-R1-0528: reasoning-enabled· Nejumi Leaderboard 4 data docs0.775
52Qwen3.5 27BQwen/Qwen3.5-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.775
53GPT 5.1openai/gpt-5.1-2025-11-13: high-effort· Nejumi Leaderboard 4 data docs0.774
54Claude Haiku 4.5anthropic/claude-haiku-4-5-20251001: extended-thinking· Nejumi Leaderboard 4 data docs0.774
55Qwen3.5 122B-A10BQwen/Qwen3.5-122B-A10B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.773
56Qwen 3 235B A22BQwen/Qwen3-235B-A22B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.773
57OpenAI o3openai/o3-2025-04-16: high-effort· Nejumi Leaderboard 4 data docs0.772
58Grok 3grok-3· Nejumi Leaderboard 4 data docs0.77
59Claude Opus 4.1anthropic/claude-opus-4-1-20250805: extended-thinking· Nejumi Leaderboard 4 data docs0.77
60GLM 5.2z-ai/glm-5.2: openrouter-reasoning-xhigh· Nejumi Leaderboard 4 data docs0.77
61QwQ 32BQwen/QwQ-32B· Nejumi Leaderboard 4 data docs0.769
62Gemini 2.5 Progoogle/gemini-2.5-pro· Nejumi Leaderboard 4 data docs0.769
63Grok 4.20xai/grok-4.20-0309-reasoning· Nejumi Leaderboard 4 data docs0.768
64GLM 5.2zai-org/GLM-5.2: reasoning-max· Nejumi Leaderboard 4 data docs0.767
65o1openai/o1-2024-12-17: high-effort· Nejumi Leaderboard 4 data docs0.767
66DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash: reasoning-max· Nejumi Leaderboard 4 data docs0.765
67GPT 5openai/gpt-5-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.764
68GPT-5.6 Solopenai/gpt-5.6-sol: max-effort· Nejumi Leaderboard 4 data docs0.762
69Nova Pro 1.0us.amazon.nova-pro-v1:0· Nejumi Leaderboard 4 data docs0.762
70Qwen3.5 35B A3BQwen/Qwen3.5-35B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.762
71Grok 4.1 Fastx-ai/grok-4-1-fast-reasoning· Nejumi Leaderboard 4 data docs0.761
72Claude Sonnet 4.6anthropic/claude-sonnet-4.6: extended-thinking· Nejumi Leaderboard 4 data docs0.758
73Llama 4 Scoutmeta-llama/Llama-4-Scout-17B-16E-Instruct· Nejumi Leaderboard 4 data docs0.754
74Kimi K2.5moonshotai/Kimi-K2.5: reasoning-enabled· Nejumi Leaderboard 4 data docs0.753
75Llama 3.1 405B Instructmeta-llama/Llama-3.1-405B-Instruct-FP8· Nejumi Leaderboard 4 data docs0.752
76Qwen3 30B A3BQwen/Qwen3-30B-A3B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.75
77GPT 5.1openai/gpt-5.1-2025-11-13: none-effort· Nejumi Leaderboard 4 data docs0.749
78GPT-4.1 miniopenai/gpt-4-1-mini-2025-04-14· Nejumi Leaderboard 4 data docs0.748
79GLM 4.7 Flashzai-org/GLM-4.7-Flash: reasoning-enabled· Nejumi Leaderboard 4 data docs0.748
80Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.748
81GPT 4.1openai/gpt-4-1-2025-04-14· Nejumi Leaderboard 4 data docs0.748
82Qwen3 Next 80B A3BQwen/Qwen3-Next-80B-A3B-Thinking: reasoning-enabled· Nejumi Leaderboard 4 data docs0.747
83MiniMax M2.1MiniMaxAI/MiniMax-M2.1: reasoning-enabled· Nejumi Leaderboard 4 data docs0.746
84Qwen: Qwen3 VL 8B ThinkingQwen/Qwen3-VL-8B-Thinking· Nejumi Leaderboard 4 data docs0.745
85Qwen3 Next 80B A3BQwen/Qwen3-Next-80B-A3B-Thinking· Nejumi Leaderboard 4 data docs0.744
86Mistral Smallmistral/mistral-small-2503· Nejumi Leaderboard 4 data docs0.744
87Claude Haiku 3.5anthropic/claude-3.5-haiku-20241022· Nejumi Leaderboard 4 data docs0.744
88Gemma 4 E4B-itgoogle/gemma-4-E4B-it· Nejumi Leaderboard 4 data docs0.743
89Qwen 3 235B A22B Thinking 2507Qwen/Qwen3-235B-A22B-Thinking-2507: reasoning-enabled· Nejumi Leaderboard 4 data docs0.743
90Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8· Nejumi Leaderboard 4 data docs0.742
91Qwen3.5 9BQwen/Qwen3.5-9B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.742
92GLM 4.6zai-org/GLM-4.6-FP8: reasoning-enabled· Nejumi Leaderboard 4 data docs0.739
93GPT OSS 120Bopenai/gpt-oss-120b: reasoning-enabled· Nejumi Leaderboard 4 data docs0.739
94Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: extended-thinking· Nejumi Leaderboard 4 data docs0.738
95Qwen3.5 4BQwen/Qwen3.5-4B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.737
96Claude Sonnet 4anthropic/claude-sonnet-4-20250514: extended-thinking· Nejumi Leaderboard 4 data docs0.735
97Gemini 2.5 Flashgoogle/gemini-2.5-flash· Nejumi Leaderboard 4 data docs0.735
98Qwen3 14BQwen/Qwen3-14B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.731
99Mistral Large 3 675b Instructmistralai/Mistral-Large-3-675B-Instruct-2512· Nejumi Leaderboard 4 data docs0.729
100Llama 3.3 70B Instructmeta-llama/Llama-3.3-70B-Instruct· Nejumi Leaderboard 4 data docs0.728

Showing 51–100 of 126 results.

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