Skip to content

Benchmark

Horangi 4: GLP_수학적추론

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.22

Score distribution

0.774
Mean
0.882
Median
0.229
Std dev
0.422
10th percentile
0.965
90th percentile
0.02
Min
0.020.985
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.22 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 docs0.985
2GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.98
3Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.98
4Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.975
5GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.975
6Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.975
7GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.97
8Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.968
9GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.965
10Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.963
11Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.963
12GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.963
13DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.959
14Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.958
15Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.948
16Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.947
17Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.947
18Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.947
19Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.945
20GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.943
21Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.939
22Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.939
23GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.938
24GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.938
25GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.938
26Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.937
27Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.936
28GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.935
29Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.93
30Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.927
31Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.924
32Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.921
33GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.915
34MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.914
35Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.914
36Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.911
37Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.908
38MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.907
39GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.905
40Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.898
41Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.888
42Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.882
43Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.881
44MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.878
45GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.875
46GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.862
47GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.86
48GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.86
49Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.828
50Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.82

Showing 1–50 of 83 results.

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