Skip to content

Benchmark

Horangi 4: ALT_제어성

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
1GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.95
2GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.938
3GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.933
4GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.929
5GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.929
6GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.925
7GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.925
8GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.925
9Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.925
10Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.925
11GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.917
12Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.913
13Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.913
14Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.913
15GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.913
16GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.909
17Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.908
18GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.904
19GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.9
20GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.897
21Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.896
22Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.896
23Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.894
24Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.888
25MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.888
26Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.888
27Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.887
28MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.885
29Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.88
30Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.88
31Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.879
32Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.879
33Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.875
34Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.875
35GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.872
36GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.868
37GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.867
38Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.867
39Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.865
40Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.863
41Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.863
42Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.858
43Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.858
44Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.858
45GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.855
46Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.852
47Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.85
48DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.85
49Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.85
50Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.842

Showing 1–50 of 83 results.

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