Skip to content

Benchmark

Horangi 4: 가치정렬성능(ALT)_AVG

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.99

Score distribution

0.722
Mean
0.745
Median
0.083
Std dev
0.62
10th percentile
0.801
90th percentile
0.346
Min
0.3460.848
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.99 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 docs0.848
2Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.816
3Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.813
4Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.812
5GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.811
6Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.811
7GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.808
8GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.804
9Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.801
10Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.8
11Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.8
12Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.796
13Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.796
14Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.789
15Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.789
16GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.786
17GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.784
18Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.783
19GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.78
20Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.78
21GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.777
22DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.775
23GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.775
24Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.772
25GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.77
26Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.766
27Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.766
28Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.765
29Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.764
30GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.763
31Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.763
32Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.76
33GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.759
34Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.755
35Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.754
36GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.753
37Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.752
38Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.751
39GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.751
40Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.75
41GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.749
42GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.745
43Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.745
44GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.743
45GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.734
46GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.733
47Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.733
48Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.732
49Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.731
50Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.731

Showing 1–50 of 83 results.

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