Skip to content

Benchmark

Horangi 4 subset: kobbq

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.30

Score distribution

0.831
Mean
0.87
Median
0.145
Std dev
0.66
10th percentile
0.96
90th percentile
0.31
Min
0.311
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.30 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
1Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs1
2Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.99
3Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.98
4Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.98
5Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.98
6Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.97
7GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.97
8Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.96
9GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.96
10GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.96
11Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.95
12GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.95
13GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.95
14Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.947
15Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.94
16Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.94
17Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.94
18GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.94
19GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.94
20Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.94
21Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.93
22Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.93
23GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.93
24GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.93
25GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.93
26Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.92
27GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.92
28Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.92
29DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.91
30GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.91
31Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.9
32GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.9
33GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.9
34GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.89
35Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.89
36Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.89
37Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.88
38MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.88
39MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.88
40GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.879
41Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.87
42Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.87
43Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.87
44Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.87
45Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.87
46Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.87
47Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.87
48Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.86
49GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.86
50GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.86

Showing 1–50 of 83 results.

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