Skip to content

Benchmark

Horangi 4 subset: ko_balt_700_semantic

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.71

Score distribution

0.636
Mean
0.677
Median
0.18
Std dev
0.41
10th percentile
0.82
90th percentile
0.1
Min
0.10.91
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.71 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
51Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.643
52Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.64
53GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.63
54Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.63
55GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.59
56MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.59
57MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.578
58Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.56
59Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.56
60GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.55
61GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.54
62Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.54
63GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.53
64Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.53
65Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.52
66Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.49
67Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.49
68GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.48
69GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.469
70Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.46
71Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.46
72MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.45
73Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.42
74Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.42
75Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.41
76Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.38
77Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.37
78GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.36
79Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.24
80Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.17
81Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.16
82Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.12
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.1

Showing 51–83 of 83 results.

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