Skip to content

Benchmark

Horangi 4 subset: hrm8k

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.18

Score distribution

0.837
Mean
0.91
Median
0.176
Std dev
0.61
10th percentile
0.96
90th percentile
0.04
Min
0.040.97
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.18 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 docs0.97
2GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.97
3Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.97
4Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.96
5Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.96
6Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.96
7Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.96
8GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.96
9GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.96
10Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.96
11Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.96
12Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.96
13Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.96
14DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.958
15Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.95
16Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.95
17GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.95
18Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.95
19Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.949
20Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.948
21Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.948
22Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.94
23Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.94
24GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.94
25MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.94
26Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.939
27Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.93
28Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.93
29GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.93
30GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.93
31GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.93
32Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.93
33Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.93
34Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.93
35Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.929
36MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.929
37Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.92
38GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.92
39GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.92
40GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.92
41Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.918
42Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.91
43GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.91
44GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.91
45GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.91
46GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.91
47GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.909
48Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.904
49Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.9
50GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.898

Showing 1–50 of 83 results.

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