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
1Qwen3.6 27BQwen/Qwen3.6-27B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.825
2Gemini 3.6 Flashgoogle/gemini-3.6-flash· Nejumi Leaderboard 4 data docs0.823
3Qwen3 Next 80B A3B InstructQwen/Qwen3-Next-80B-A3B-Instruct· Nejumi Leaderboard 4 data docs0.823
4Claude Opus 5anthropic/claude-opus-5: adaptive-thinking-max· Nejumi Leaderboard 4 data docs0.822
5Claude Fable 5anthropic/claude-fable-5: adaptive-thinking-max with fallback to Opus 4.8· Nejumi Leaderboard 4 data docs0.82
6Gemini 3 Pro Previewgoogle/gemini-3-pro-preview· Nejumi Leaderboard 4 data docs0.818
7Gemini 3.5 Flashgoogle/gemini-3.5-flash· Nejumi Leaderboard 4 data docs0.817
8Gemma 4 31B ITgoogle/gemma-4-31b-it· Nejumi Leaderboard 4 data docs0.815
9Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview· Nejumi Leaderboard 4 data docs0.811
10GPT-5.4 miniopenai/gpt-5.4-mini-2026-03-17: high-effort· Nejumi Leaderboard 4 data docs0.811
11Kimi K3moonshotai/kimi-k3: reasoning-max· Nejumi Leaderboard 4 data docs0.81
12Claude Opus 4.7anthropic/claude-opus-4.7: adaptive-thinking-xhigh· Nejumi Leaderboard 4 data docs0.808
13Claude Opus 4anthropic/claude-opus-4-20250514: no-thinking· Nejumi Leaderboard 4 data docs0.808
14Grok 4.5xai/grok-4.5: reasoning-high· Nejumi Leaderboard 4 data docs0.807
15GPT 5.4openai/gpt-5.4-2026-03-05: xhigh-effort· Nejumi Leaderboard 4 data docs0.805
16GLM 4.7zai-org/GLM-4.7: reasoning-enabled· Nejumi Leaderboard 4 data docs0.804
17Nova Lite 1.0us.amazon.nova-lite-v1:0· Nejumi Leaderboard 4 data docs0.804
18Qwen3.6 Max Previewqwen/qwen3.6-max-preview: openrouter-reasoning· Nejumi Leaderboard 4 data docs0.803
19Gemini 3 Flashgoogle/gemini-3-flash-preview· Nejumi Leaderboard 4 data docs0.803
20Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it· Nejumi Leaderboard 4 data docs0.803
21Claude Opus 4.5anthropic/claude-opus-4.5-20251125: no-thinking· Nejumi Leaderboard 4 data docs0.802
22Claude Sonnet 4anthropic/claude-sonnet-4-20250514: no-thinking· Nejumi Leaderboard 4 data docs0.802
23Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: no-thinking· Nejumi Leaderboard 4 data docs0.799
24Claude Opus 4.5anthropic/claude-opus-4.5-20251125: extended-thinking· Nejumi Leaderboard 4 data docs0.798
25o4 Miniopenai/o4-mini-2025-04-16· Nejumi Leaderboard 4 data docs0.798
26DeepSeek V4 Prodeepseek/deepseek-v4-pro: thinking-max· Nejumi Leaderboard 4 data docs0.797
27GPT 5.2openai/gpt-5.2-2025-12-11: xhigh-effort· Nejumi Leaderboard 4 data docs0.796
28GPT-5.6 Terraopenai/gpt-5.6-terra: max-effort· Nejumi Leaderboard 4 data docs0.795
29Claude Opus 4.6anthropic/claude-opus-4-6: extended-thinking· Nejumi Leaderboard 4 data docs0.794
30DeepSeek V3deepseek-ai/DeepSeek-V3-0324· Nejumi Leaderboard 4 data docs0.793
31Qwen3.6 35B A3BQwen/Qwen3.6-35B-A3B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.792
32DeepSeek V4 Prodeepseek-ai/DeepSeek-V4-Pro: reasoning-max· Nejumi Leaderboard 4 data docs0.79
33Claude Opus 4.8anthropic/claude-opus-4.8: adaptive-thinking-xhigh· Nejumi Leaderboard 4 data docs0.79
34QwQ 32BQwen/QwQ-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.79
35GPT 5.5openai/gpt-5.5-2026-04-23: high-effort· Nejumi Leaderboard 4 data docs0.788
36Grok 4grok-4· Nejumi Leaderboard 4 data docs0.787
37Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite-preview· Nejumi Leaderboard 4 data docs0.787
38DeepSeek V3.2deepseek-ai/DeepSeek-V3.2: reasoning-enabled· Nejumi Leaderboard 4 data docs0.787
39Qwen3 32BQwen/Qwen3-32B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.786
40GPT 5.4openai/gpt-5.4-2026-03-05: high-effort· Nejumi Leaderboard 4 data docs0.786
41GPT 5.5openai/gpt-5.5-2026-04-23: xhigh-effort· Nejumi Leaderboard 4 data docs0.784
42Kimi K2 Thinkingmoonshotai/kimi-k2-thinking· Nejumi Leaderboard 4 data docs0.783
43Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929: extended-thinking· Nejumi Leaderboard 4 data docs0.783
44GLM 5zai-org/GLM-5: reasoning-enabled· Nejumi Leaderboard 4 data docs0.782
45o3 Miniopenai/o3-mini-2025-01-31· Nejumi Leaderboard 4 data docs0.78
46GPT-5.6 Lunaopenai/gpt-5.6-luna: max-effort· Nejumi Leaderboard 4 data docs0.78
47Qwen3 VL 32B ThinkingQwen/Qwen3-VL-32B-Thinking· Nejumi Leaderboard 4 data docs0.777
48MiniMax M3MiniMaxAI/MiniMax-M3: reasoning-enabled· Nejumi Leaderboard 4 data docs0.777
49DeepSeek Reasonerdeepseek/DeepSeek-V3.2 (Thinking Mode)· Nejumi Leaderboard 4 data docs0.776
50GPT-4o miniopenai/gpt-4o-mini-2024-07-18· Nejumi Leaderboard 4 data docs0.775

Showing 1–50 of 126 results.

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