Skip to content

Benchmark

Nejumi 4: GLP_構文解析

Higher scores are better.

Models measured
114
Scores recorded
126
Sources
1
IQ weight
1.70

Score distribution

0.745
Mean
0.802
Median
0.17
Std dev
0.583
10th percentile
0.875
90th percentile
0
Min
00.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.70 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
1GPT 5.5openai/gpt-5.5-2026-04-23: xhigh-effort· Nejumi Leaderboard 4 data docs0.9
2Gemini 3 Flashgoogle/gemini-3-flash-preview· Nejumi Leaderboard 4 data docs0.898
3GPT 5.5openai/gpt-5.5-2026-04-23: high-effort· Nejumi Leaderboard 4 data docs0.895
4Gemini 3 Pro Previewgoogle/gemini-3-pro-preview· Nejumi Leaderboard 4 data docs0.892
5Gemma 4 31B ITgoogle/gemma-4-31b-it· Nejumi Leaderboard 4 data docs0.888
6Claude Fable 5anthropic/claude-fable-5: adaptive-thinking-max with fallback to Opus 4.8· Nejumi Leaderboard 4 data docs0.887
7GPT 5.1openai/gpt-5.1-2025-11-13: high-effort· Nejumi Leaderboard 4 data docs0.883
8GPT 5.4openai/gpt-5.4-2026-03-05: xhigh-effort· Nejumi Leaderboard 4 data docs0.882
9GPT-5.6 Terraopenai/gpt-5.6-terra: max-effort· Nejumi Leaderboard 4 data docs0.88
10GPT-5.6 Solopenai/gpt-5.6-sol: max-effort· Nejumi Leaderboard 4 data docs0.88
11GPT-5.6 Lunaopenai/gpt-5.6-luna: max-effort· Nejumi Leaderboard 4 data docs0.878
12Gemini 3.5 Flashgoogle/gemini-3.5-flash· Nejumi Leaderboard 4 data docs0.878
13Claude Opus 4.6anthropic/claude-opus-4-6: extended-thinking· Nejumi Leaderboard 4 data docs0.875
14Gemini 2.5 Progoogle/gemini-2.5-pro· Nejumi Leaderboard 4 data docs0.875
15Claude Sonnet 4.6anthropic/claude-sonnet-4.6: extended-thinking· Nejumi Leaderboard 4 data docs0.872
16Qwen3.5 397B A17BQwen/Qwen3.5-397B-A17B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.872
17GPT 5.4openai/gpt-5.4-2026-03-05: high-effort· Nejumi Leaderboard 4 data docs0.87
18Gemini 3.6 Flashgoogle/gemini-3.6-flash· Nejumi Leaderboard 4 data docs0.868
19Claude Opus 4.5anthropic/claude-opus-4.5-20251125: extended-thinking· Nejumi Leaderboard 4 data docs0.867
20Grok 4.5xai/grok-4.5: reasoning-high· Nejumi Leaderboard 4 data docs0.867
21OpenAI o3openai/o3-2025-04-16: high-effort· Nejumi Leaderboard 4 data docs0.865
22GPT 5.2openai/gpt-5.2-2025-12-11: xhigh-effort· Nejumi Leaderboard 4 data docs0.863
23o1openai/o1-2024-12-17: high-effort· Nejumi Leaderboard 4 data docs0.862
24Claude Opus 4.7anthropic/claude-opus-4.7: adaptive-thinking-xhigh· Nejumi Leaderboard 4 data docs0.857
25Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview· Nejumi Leaderboard 4 data docs0.857
26Claude Opus 4.8anthropic/claude-opus-4.8: adaptive-thinking-xhigh· Nejumi Leaderboard 4 data docs0.855
27GLM 4.7zai-org/GLM-4.7: reasoning-enabled· Nejumi Leaderboard 4 data docs0.855
28GPT 5openai/gpt-5-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.853
29Qwen3.6 Max Previewqwen/qwen3.6-max-preview: openrouter-reasoning· Nejumi Leaderboard 4 data docs0.852
30DeepSeek V4 Flashdeepseek-ai/DeepSeek-V4-Flash: reasoning-max· Nejumi Leaderboard 4 data docs0.85
31Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it· Nejumi Leaderboard 4 data docs0.85
32DeepSeek R1deepseek-ai/DeepSeek-R1-0528: reasoning-enabled· Nejumi Leaderboard 4 data docs0.848
33GPT-5.4 miniopenai/gpt-5.4-mini-2026-03-17: high-effort· Nejumi Leaderboard 4 data docs0.848
34Qwen3.5 122B-A10BQwen/Qwen3.5-122B-A10B: reasoning-enabled· Nejumi Leaderboard 4 data docs0.847
35Grok 4.1 Fastx-ai/grok-4-1-fast-reasoning· Nejumi Leaderboard 4 data docs0.845
36Kimi K3moonshotai/kimi-k3: reasoning-max· Nejumi Leaderboard 4 data docs0.845
37Llama 3.1 405B Instructmeta-llama/Llama-3.1-405B-Instruct-FP8· Nejumi Leaderboard 4 data docs0.845
38DeepSeek Reasonerdeepseek/DeepSeek-V3.2 (Thinking Mode)· Nejumi Leaderboard 4 data docs0.843
39GLM 4.6zai-org/GLM-4.6-FP8: reasoning-enabled· Nejumi Leaderboard 4 data docs0.842
40Claude Opus 5anthropic/claude-opus-5: adaptive-thinking-max· Nejumi Leaderboard 4 data docs0.842
41GPT 4.1openai/gpt-4-1-2025-04-14· Nejumi Leaderboard 4 data docs0.838
42DeepSeek V3.2deepseek-ai/DeepSeek-V3.2: reasoning-enabled· Nejumi Leaderboard 4 data docs0.837
43MiniMax M3MiniMaxAI/MiniMax-M3: reasoning-enabled· Nejumi Leaderboard 4 data docs0.833
44Claude Sonnet 3.7anthropic/claude-3.7-sonnet-20250219: extended-thinking· Nejumi Leaderboard 4 data docs0.832
45o3 Miniopenai/o3-mini-2025-01-31· Nejumi Leaderboard 4 data docs0.828
46Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite-preview· Nejumi Leaderboard 4 data docs0.825
47Claude Sonnet 4.5anthropic/claude-sonnet-4-5-20250929: extended-thinking· Nejumi Leaderboard 4 data docs0.823
48GLM 5zai-org/GLM-5: reasoning-enabled· Nejumi Leaderboard 4 data docs0.823
49GPT-5 nanoopenai/gpt-5-nano-2025-08-07: high-effort· Nejumi Leaderboard 4 data docs0.823
50Grok 3 Minigrok-3-mini· Nejumi Leaderboard 4 data docs0.823

Showing 1–50 of 126 results.

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