Skip to content

Benchmark

Horangi 4 subset: ko_truthful_qa

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
2.32

Score distribution

0.801
Mean
0.83
Median
0.139
Std dev
0.6
10th percentile
0.95
90th percentile
0.35
Min
0.350.98
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.32 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
51DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.8
52GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.8
53MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.8
54Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.79
55Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.788
56GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.78
57Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.78
58GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.77
59GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.77
60Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.77
61MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.77
62Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.77
63MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.768
64GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.74
65GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.74
66Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.74
67GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.72
68Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.71
69Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.71
70GPT-4.1 nanogpt-4.1-nano· Horangi Korean Leaderboard 4 data docs0.7
71Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.67
72Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.65
73Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.63
74Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.61
75Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.6
76Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.6
77Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.571
78Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.5
79Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.49
80Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.48
81Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.46
82Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.35
83Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.35

Showing 51–83 of 83 results.

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