Skip to content

Benchmark

Horangi 4 subset: haerae_bench_v1_wo_rc

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.09

Score distribution

0.851
Mean
0.888
Median
0.142
Std dev
0.697
10th percentile
0.99
90th percentile
0.283
Min
0.2831
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.09 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
51Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.859
52Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.859
53Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.859
54Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.857
55Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.848
56Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.848
57Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.848
58Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.828
59Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.808
60Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.798
61Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.798
62Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.788
63Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.778
64Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.778
65MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.776
66Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.773
67Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.768
68Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.747
69GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.747
70GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.737
71MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.737
72GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.727
73Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.717
74Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.707
75Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.697
76Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.646
77Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.646
78Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.626
79Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.626
80Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.535
81Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.414
82Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.343
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.283

Showing 51–83 of 83 results.

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