Skip to content

Benchmark

Horangi 4 subset: ko_hle

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.33

Score distribution

0.212
Mean
0.19
Median
0.131
Std dev
0.07
10th percentile
0.424
90th percentile
0.02
Min
0.020.531
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.33 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
51MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.144
52Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.141
53GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.14
54Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.133
55Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.13
56Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.13
57Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.12
58Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.11
59Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.11
60GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.11
61GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.11
62Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.11
63GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.102
64Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.1
65GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.1
66GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.1
67Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.1
68Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.09
69Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.09
70Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.08
71Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.08
72Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.08
73Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.08
74Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.07
75Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.07
76Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.06
77GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.06
78Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.06
79Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.05
80Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.04
81Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.04
82Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.04
83Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.02

Showing 51–83 of 83 results.

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