Skip to content

Benchmark

Horangi 4: 범용언어성능(GLP)_AVG

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.83

Score distribution

0.644
Mean
0.674
Median
0.146
Std dev
0.466
10th percentile
0.803
90th percentile
0.126
Min
0.1260.839
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.83 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
51MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.654
52Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.651
53MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.645
54Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.641
55Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.619
56GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.608
57Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.599
58GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.575
59GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.575
60Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.564
61Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.562
62Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.562
63Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.556
64GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.555
65Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.545
66GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.544
67GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.519
68Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.512
69Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.499
70Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.499
71GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.496
72Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.493
73Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.485
74Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.477
75Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.466
76GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.466
77Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.422
78Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.39
79Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.388
80Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.331
81Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.273
82Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.207
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.126

Showing 51–83 of 83 results.

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