Skip to content

Benchmark

Horangi 4 subset: kmmlu_pro

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.93

Score distribution

0.7
Mean
0.74
Median
0.173
Std dev
0.5
10th percentile
0.9
90th percentile
0.13
Min
0.130.95
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
1Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.95
2GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.95
3GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.94
4Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.91
5GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.91
6GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.91
7Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.9
8Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.9
9GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.9
10Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.899
11Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.899
12Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.89
13GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.887
14Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.88
15Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.88
16Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.86
17Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.84
18Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.83
19Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.83
20Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.83
21GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.82
22Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.818
23Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.81
24Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.81
25GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.81
26Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.81
27DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.798
28Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.794
29Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.79
30Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.788
31Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.77
32GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.77
33GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.77
34Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.768
35Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.768
36GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.763
37Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.76
38GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.758
39GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.747
40Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.747
41GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.74
42Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.74
43GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.73
44Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.722
45Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.72
46GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.71
47Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.71
48GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.7
49Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.68
50MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.68

Showing 1–50 of 83 results.

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