Skip to content

Benchmark

Horangi 4 subset: ko_balt_700_syntax

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.72

Score distribution

0.593
Mean
0.67
Median
0.223
Std dev
0.25
10th percentile
0.85
90th percentile
0.09
Min
0.090.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.72 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
1GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.9
2Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.88
3GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.88
4Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.87
5Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.87
6Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.87
7Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.86
8Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.85
9Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.85
10GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.85
11Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.84
12GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.84
13GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.82
14Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.81
15Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.81
16Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.802
17Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.8
18GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.8
19Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.78
20GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.78
21Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.77
22GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.77
23Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.77
24GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.76
25GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.758
26Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.745
27Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.733
28Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.73
29DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.73
30GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.727
31Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.727
32Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.72
33Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.72
34GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.72
35Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.72
36Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.716
37Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.68
38GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.677
39Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.67
40GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.67
41GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.67
42Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.67
43GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.633
44Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.63
45Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.62
46GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.6
47MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.6
48Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.586
49Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.585
50MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.574

Showing 1–50 of 83 results.

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