Skip to content

Benchmark

Horangi 4 subset: ko_aime2025

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.39

Score distribution

0.711
Mean
0.867
Median
0.296
Std dev
0.233
10th percentile
0.967
90th percentile
0
Min
01
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.39 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
51GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.75
52GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.733
53Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.7
54Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.7
55Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.667
56GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.667
57Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.633
58Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.633
59Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.633
60Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.6
61Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.5
62Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.467
63GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.433
64Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.433
65GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.4
66Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.4
67Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.367
68Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.367
69Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.333
70Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.333
71Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.333
72GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.31
73Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.3
74Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.233
75Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.233
76GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.2
77Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.2
78Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.167
79Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.167
80Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.0667
81Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.0333
82GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.0333
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0

Showing 51–83 of 83 results.

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