Skip to content

Benchmark

Horangi 4 subset: ko_balt_700_syntax

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.72

Score distribution

0.593
Mean
0.67
Median
0.223
Std dev
0.25
10th percentile
0.85
90th percentile
0.09
Min
0.090.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.72 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 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.571
52Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.57
53Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.566
54Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.55
55MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.546
56Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.525
57Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.5
58GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.47
59GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.45
60Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.44
61GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.43
62GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.42
63Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.42
64MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.404
65Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.4
66Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.39
67GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.38
68Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.37
69Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.36
70Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.33
71Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.32
72GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.273
73Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.27
74Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.27
75Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.25
76Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.24
77Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.24
78Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.2
79GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.2
80Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.12
81Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.12
82Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.1
83Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.09

Showing 51–83 of 83 results.

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