Skip to content

Benchmark

Horangi 4 subset: ifeval_ko

Instruction following benchmarks measure how closely models follow instructions. Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.72

Score distribution

0.832
Mean
0.858
Median
0.109
Std dev
0.749
10th percentile
0.925
90th percentile
0.28
Min
0.280.95
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
51Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.842
52Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.837
53Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.835
54Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.835
55Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.83
56Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.83
57MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.813
58Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.806
59GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.805
60Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.797
61Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.797
62Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.796
63GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.796
64Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.793
65Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.793
66GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.79
67Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.787
68Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.785
69GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.783
70MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.783
71Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.773
72GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.767
73Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.761
74GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.758
75Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.749
76Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.747
77Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.731
78Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.715
79Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.668
80Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.576
81Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.479
82Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.407
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.28

Showing 51–83 of 83 results.

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