Skip to content

Benchmark

Horangi 4 subset: kmmlu

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.95

Score distribution

0.776
Mean
0.82
Median
0.141
Std dev
0.61
10th percentile
0.91
90th percentile
0.21
Min
0.210.94
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.95 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
1Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.94
2GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.94
3Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.939
4GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.93
5Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.92
6GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.92
7GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.917
8Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.91
9Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.91
10Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.9
11Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.9
12Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.9
13GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.9
14GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.9
15GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.9
16Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.9
17Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.89
18Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.889
19GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.88
20GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.88
21GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.87
22Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.86
23Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.86
24Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.86
25GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.85
26Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.85
27Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.85
28Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.85
29Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.85
30GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.845
31Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.84
32GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.84
33Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.84
34Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.84
35Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.83
36DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.83
37Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.83
38GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.83
39GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.83
40Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.83
41Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.828
42Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.82
43Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.82
44Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.81
45Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.81
46Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.81
47Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.81
48Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.8
49GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.8
50Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.8

Showing 1–50 of 83 results.

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