Skip to content

Benchmark

Horangi 4 subset: ko_hallulens_nonexistent

Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
0.13

Score distribution

0.691
Mean
0.75
Median
0.203
Std dev
0.33
10th percentile
0.93
90th percentile
0.22
Min
0.220.99
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.13 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
51GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.71
52Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.71
53Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.68
54GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.67
55Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.65
56Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.64
57Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.63
58Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.63
59GLM 4.5 Airglm-4.5-air· Horangi Korean Leaderboard 4 data docs0.616
60Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.61
61GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.61
62GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.6
63GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.58
64GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.52
65GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.51
66GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.49
67MiniMax M2.5minimax-m2.5· Horangi Korean Leaderboard 4 data docs0.48
68GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.47
69MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.467
70Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.46
71Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.45
72GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.43
73GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.43
74GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.37
75MiniMax M2.7minimax-m2.7· Horangi Korean Leaderboard 4 data docs0.33
76Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.32
77Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.32
78GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.31
79Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.29
80Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.26
81GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.26
82Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.25
83Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.22

Showing 51–83 of 83 results.

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