Skip to content

Benchmark

Horangi 4: GLP_표현

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.60

Score distribution

0.64
Mean
0.657
Median
0.068
Std dev
0.611
10th percentile
0.68
90th percentile
0.176
Min
0.1760.695
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.60 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
51Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.648
52Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.648
53Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.647
54Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.646
55GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.644
56Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.644
57Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.644
58Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.641
59Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.639
60Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.639
61Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.639
62Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.637
63Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.636
64Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.634
65Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.631
66Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.631
67GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.631
68MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.63
69Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.627
70MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.625
71Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.624
72Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.624
73Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.616
74Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.614
75GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.611
76Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.595
77Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.567
78Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.565
79Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.56
80Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.534
81Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.492
82Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.382
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.176

Showing 51–83 of 83 results.

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