Skip to content

Benchmark

Horangi 4 subset: ko_hle

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.33

Score distribution

0.212
Mean
0.19
Median
0.131
Std dev
0.07
10th percentile
0.424
90th percentile
0.02
Min
0.020.531
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.33 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 docs0.531
2GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.52
3Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.5
4GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.47
5GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.47
6GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.465
7Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.45
8Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.45
9Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.424
10Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.41
11GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.4
12Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.37
13Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.37
14GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.365
15Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.35
16GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.34
17Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.313
18Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.29
19Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.283
20MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.282
21GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.28
22Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.277
23Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.276
24Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.273
25GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.268
26DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.268
27Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.267
28GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.26
29GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.26
30Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.25
31Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.25
32Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.247
33GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.245
34Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.22
35GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.22
36MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.212
37Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.206
38Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.2
39Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.198
40Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.192
41GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.19
42Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.19
43MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.188
44Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.182
45Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.173
46GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.17
47Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.16
48GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.153
49Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.152
50GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.149

Showing 1–50 of 83 results.

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