Skip to content

Benchmark

Horangi 4: GLP_논리적추론

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.08

Score distribution

0.795
Mean
0.83
Median
0.118
Std dev
0.695
10th percentile
0.88
90th percentile
0.145
Min
0.1450.905
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.08 for chat models, measured over 79 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.805
52GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.805
53DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.8
54GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.8
55Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.799
56Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.795
57Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.795
58GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.79
59Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.77
60MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.769
61Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.765
62Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.765
63Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.76
64GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.76
65MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.753
66MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.739
67GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.735
68Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.735
69Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.735
70Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.725
71Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.725
72Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.715
73Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.715
74GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.7
75Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.695
76Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.695
77Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.692
78Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.655
79Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.645
80Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.57
81Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.41
82Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.37
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.145

Showing 51–83 of 83 results.

Data credits: Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results