Skip to content

Benchmark

Horangi 4 subset: ko_balt_700_semantic

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.71

Score distribution

0.636
Mean
0.677
Median
0.18
Std dev
0.41
10th percentile
0.82
90th percentile
0.1
Min
0.10.91
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.71 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 docs0.91
2Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.87
3Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.85
4GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.84
5GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.84
6GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.83
7Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.828
8Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.82
9GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.82
10Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.813
11Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.806
12Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.8
13GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.8
14GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.8
15GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.8
16GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.8
17Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.79
18Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.78
19Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.78
20Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.77
21GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.77
22Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.763
23Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.76
24Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.76
25Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.758
26Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.75
27Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.747
28GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.745
29Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.74
30GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.74
31GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.73
32GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.73
33Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.727
34Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.72
35Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.72
36Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.717
37GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.71
38Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.7
39Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.7
40DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.69
41Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.68
42Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.677
43Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.67
44Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.67
45GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.67
46GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.67
47Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.667
48Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.66
49MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.66
50Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.66

Showing 1–50 of 83 results.

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