Skip to content

Benchmark

Horangi 4 subset: squad_kor_v1

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.31

Score distribution

0.771
Mean
0.821
Median
0.166
Std dev
0.691
10th percentile
0.877
90th percentile
0.0889
Min
0.08890.903
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.31 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
1Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.903
2Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.901
3Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.891
4Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.889
5Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.889
6Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.885
7Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.882
8Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.882
9Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.877
10GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.873
11Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.872
12GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.872
13Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.871
14Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.87
15Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.87
16Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.87
17Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.868
18GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.868
19GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.867
20Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.865
21GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.863
22GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.86
23Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.86
24GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.859
25Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.854
26Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.854
27GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.852
28Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.849
29Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.849
30GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.848
31GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.847
32Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.847
33GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.846
34Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.842
35Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.841
36Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.841
37MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.837
38Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.832
39GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.831
40Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.827
41MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.827
42Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.821
43DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.82
44GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.811
45Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.807
46GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.803
47Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.801
48GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.797
49Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.796
50Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.79

Showing 1–50 of 83 results.

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