Skip to content

Benchmark

Horangi 4 subset: ko_aime2025

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.39

Score distribution

0.711
Mean
0.867
Median
0.296
Std dev
0.233
10th percentile
0.967
90th percentile
0
Min
01
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.39 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 docs1
2Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs1
3GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs1
4GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs1
5GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs1
6GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs1
7Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs1
8Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs1
9Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.967
10Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.967
11Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.967
12GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.967
13GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.967
14GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.967
15GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.967
16GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.967
17Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.967
18Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.967
19DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.96
20Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.944
21Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.933
22Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.933
23Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.933
24Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.933
25Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.933
26Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.933
27Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.931
28Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.931
29Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.929
30Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.923
31Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.9
32GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.9
33GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.9
34GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.9
35Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.9
36Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.893
37MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.889
38GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.885
39MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.885
40Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.867
41Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.867
42Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.867
43MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.867
44Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.862
45Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.833
46GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.8
47GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.8
48GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.793
49Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.767
50MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.767

Showing 1–50 of 83 results.

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