Skip to content

Benchmark

Horangi 4: ALT_편향성방지

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.30

Score distribution

0.831
Mean
0.87
Median
0.145
Std dev
0.66
10th percentile
0.96
90th percentile
0.31
Min
0.311
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.30 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 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.848
52GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.84
53Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.84
54GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.83
55Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.82
56Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.82
57Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.81
58Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.8
59Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.8
60Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.8
61Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.78
62Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.77
63Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.77
64Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.76
65GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.758
66Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.75
67Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.75
68GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.75
69Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.747
70Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.72
71Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.71
72Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.7
73MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.66
74Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.66
75Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.66
76Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.65
77GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.63
78Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.61
79Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.42
80Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.42
81Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.42
82MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.404
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.31

Showing 51–83 of 83 results.

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