Skip to content

Benchmark

Horangi 4: FINAL_SCORE

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.93

Score distribution

0.683
Mean
0.712
Median
0.111
Std dev
0.565
10th percentile
0.797
90th percentile
0.236
Min
0.2360.841
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.93 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 docs0.841
2Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.826
3GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.818
4Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.812
5Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.808
6GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.807
7Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.802
8Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.801
9GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.797
10Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.787
11Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.786
12GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.783
13Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.775
14GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.772
15Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.771
16GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.77
17Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.77
18Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.769
19GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.767
20Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.767
21Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.763
22Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.762
23GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.759
24Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.759
25GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.757
26GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.755
27Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.755
28Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.753
29GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.753
30Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.747
31DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.743
32GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.743
33Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.738
34Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.736
35Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.731
36Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.728
37Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.726
38GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.721
39Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.72
40GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.719
41Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.719
42Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.712
43Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.707
44GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.707
45GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.706
46Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.703
47Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.702
48Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.698
49MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.687
50Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.684

Showing 1–50 of 83 results.

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