Skip to content

Benchmark

Horangi 4 subset: ko_hallulens_wikiqa

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.39

Score distribution

0.32
Mean
0.32
Median
0.153
Std dev
0.1
10th percentile
0.54
90th percentile
0.03
Min
0.030.64
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.39 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
51Qwen3.7 Plusqwen3.7-plus· Horangi Korean Leaderboard 4 data docs0.28
52MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.273
53GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.27
54Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.27
55Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.27
56Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.242
57Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.24
58GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.23
59Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.23
60Qwen3.5 35B A3Bqwen3.5-35b-a3b· Horangi Korean Leaderboard 4 data docs0.23
61Gemma 4 31B ITGemma-4-31B-IT-NVFP4: enable-thinking· Horangi Korean Leaderboard 4 data docs0.22
62Gemma 4 26B A4Bgemma-4-26B-A4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.212
63GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.212
64Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.21
65GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.21
66Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.21
67Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.2
68MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.19
69Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.18
70MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.18
71Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.15
72Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.121
73Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.12
74Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.11
75Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.1
76Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.1
77Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.0707
78Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.07
79Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.07
80Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.06
81Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.06
82Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.04
83Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.03

Showing 51–83 of 83 results.

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