Skip to content

Benchmark

Horangi 4 subset: ko_hellaswag

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.13

Score distribution

0.762
Mean
0.81
Median
0.149
Std dev
0.61
10th percentile
0.88
90th percentile
0.05
Min
0.050.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.13 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 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.9
2Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.9
3GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.9
4Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.89
5Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.89
6Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.89
7GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.89
8Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.88
9GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.88
10GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.88
11Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.88
12Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.88
13Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.873
14Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.87
15Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.87
16Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.87
17GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.87
18GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.87
19Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.87
20Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.87
21Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.86
22Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.859
23Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.85
24Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.85
25Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.85
26Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.85
27GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.845
28Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.84
29Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.84
30Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.83
31Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.83
32GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.83
33Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.83
34Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.82
35Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.82
36GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.82
37Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.82
38Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.82
39Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.81
40GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.81
41Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.81
42Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.81
43GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.8
44GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.8
45Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.8
46Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.8
47MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.798
48Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.79
49GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.79
50GLM 5V Turboglm-5v-turbo· 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