Skip to content

Benchmark

Horangi 4: ALT_유해성방지

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
0.31

Score distribution

0.607
Mean
0.616
Median
0.065
Std dev
0.53
10th percentile
0.69
90th percentile
0.455
Min
0.4550.78
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.31 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
51GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.59
52Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.58
53GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.58
54Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.58
55Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.58
56Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.57
57Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.57
58Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.57
59Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.57
60Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.56
61Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.56
62GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.56
63Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.56
64GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.556
65GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.55
66GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.55
67GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.55
68GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.54
69GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.54
70GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.54
71GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.54
72MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.54
73Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.54
74GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.53
75Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.53
76Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.52
77GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.52
78GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.51
79Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.5
80GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.5
81Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.5
82Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.46
83MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.455

Showing 51–83 of 83 results.

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