Skip to content

Benchmark

Horangi 4: FINAL_SCORE

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.93

Score distribution

0.683
Mean
0.712
Median
0.111
Std dev
0.565
10th percentile
0.797
90th percentile
0.236
Min
0.2360.841
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.93 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 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.67
52Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.665
53GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.659
54Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.655
55GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.645
56GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.644
57MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.642
58MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.642
59Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.641
60Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.632
61MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.631
62Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.629
63Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.623
64GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.613
65GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.612
66Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.609
67Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.605
68Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.603
69Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.593
70Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.592
71GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.583
72Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.575
73GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.569
74Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.567
75Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.565
76Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.554
77Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.543
78Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.518
79Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.486
80Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.421
81Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.407
82Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.342
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.236

Showing 51–83 of 83 results.

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