Skip to content

Benchmark

Horangi 4 subset: haerae_bench_v1_wo_rc

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.09

Score distribution

0.851
Mean
0.888
Median
0.142
Std dev
0.697
10th percentile
0.99
90th percentile
0.283
Min
0.2831
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.09 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 docs1
2GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs1
3GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs1
4Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.99
5Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.99
6Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.99
7GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.99
8GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.99
9GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.99
10GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.98
11Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.98
12Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.97
13Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.97
14GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.97
15Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.96
16Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.96
17Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.949
18Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.949
19GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.949
20GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.949
21GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.949
22Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.949
23Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.939
24Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.939
25Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.939
26Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.939
27Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.939
28Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.939
29Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.929
30GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.929
31GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.929
32GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.929
33GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.929
34Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.929
35GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.919
36Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.918
37Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.909
38GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.902
39MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.899
40Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.899
41Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.889
42GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.888
43Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.879
44GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.879
45GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.869
46GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.869
47MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.869
48Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.867
49DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.859
50GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.859

Showing 1–50 of 83 results.

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