Skip to content

Benchmark

Horangi 4 subset: ko_hellaswag

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.13

Score distribution

0.762
Mean
0.81
Median
0.149
Std dev
0.61
10th percentile
0.88
90th percentile
0.05
Min
0.050.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.13 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 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.77
52GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.77
53Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.77
54DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.76
55GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.76
56GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.76
57GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.76
58Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.76
59Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.758
60MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.755
61GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.74
62MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.727
63MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.717
64GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.71
65Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.71
66Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.7
67Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.69
68Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.67
69GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.67
70Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.67
71Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.66
72Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.63
73Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.62
74GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.61
75Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.61
76GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.58
77Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.55
78Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.5
79Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.495
80Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.42
81Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.36
82Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.22
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.05

Showing 51–83 of 83 results.

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