Skip to content

Benchmark

Horangi 4 subset: ko_moral

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.02

Score distribution

0.735
Mean
0.77
Median
0.121
Std dev
0.57
10th percentile
0.83
90th percentile
0.37
Min
0.370.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.02 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 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.9
2GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.88
3GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.88
4Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.87
5GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.86
6Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.85
7Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.84
8GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.84
9Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.83
10Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.83
11GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.83
12GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.83
13Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.82
14Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.82
15Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.82
16Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.82
17GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.82
18GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.82
19Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.816
20GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.81
21GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.81
22GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.81
23Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.808
24Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.8
25Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.8
26Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.8
27Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.791
28Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.79
29Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.79
30Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.79
31GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.79
32Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.79
33GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.788
34Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.786
35Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.78
36DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.78
37Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.78
38Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.78
39Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.78
40Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.78
41Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.77
42Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.77
43Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.77
44GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.77
45GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.77
46GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.77
47GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.77
48GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.77
49MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.77
50Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.77

Showing 1–50 of 83 results.

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