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
1Gemini 3.1 Pro Previewgemini-3.1-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.64
2GPT-5.6 Solgpt-5.6-sol: max-effort· Horangi Korean Leaderboard 4 data docs0.64
3GPT 5.5gpt-5.5: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.63
4Gemini 3 Pro Previewgemini-3-pro-preview: high-effort· Horangi Korean Leaderboard 4 data docs0.62
5Grok 4.5grok-4.5· Horangi Korean Leaderboard 4 data docs0.6
6Gemini 3.5 Flashgemini-3.5-flash· Horangi Korean Leaderboard 4 data docs0.59
7Gemini 3 Flashgemini-3-flash-preview· Horangi Korean Leaderboard 4 data docs0.58
8Claude Fable 5claude-fable-5: high-effort· Horangi Korean Leaderboard 4 data docs0.55
9GPT 5.4gpt-5.4-2026-03-05: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.54
10GPT-5.6 Lunagpt-5.6-luna: max-effort· Horangi Korean Leaderboard 4 data docs0.52
11GPT 5gpt-5-2025-08-07· Horangi Korean Leaderboard 4 data docs0.51
12Gemini 3.1 Flash Litegemini-3.1-flash-lite-preview· Horangi Korean Leaderboard 4 data docs0.5
13GPT 5.1gpt-5.1-2025-11-13· Horangi Korean Leaderboard 4 data docs0.48
14GPT-5.6 Terragpt-5.6-terra: max-effort· Horangi Korean Leaderboard 4 data docs0.48
15GPT 4.1gpt-4.1· Horangi Korean Leaderboard 4 data docs0.45
16GPT 5.2gpt-5.2-2025-12-11: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.45
17GPT-5.4 minigpt-5.4-mini-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.44
18Qwen3.7 Maxqwen3.7-max· Horangi Korean Leaderboard 4 data docs0.43
19Claude Opus 4.6claude-opus-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.42
20Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.42
21GLM 5glm-5· Horangi Korean Leaderboard 4 data docs0.404
22Qwen3.6 Plus Previewqwen3.6-plus-preview· Horangi Korean Leaderboard 4 data docs0.402
23Grok 4.20grok-4.20· Horangi Korean Leaderboard 4 data docs0.4
24GLM 5.2glm-5.2: high-effort· Horangi Korean Leaderboard 4 data docs0.394
25MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.394
26Qwen3.5 397B A17Bqwen3.5-397b-a17b· Horangi Korean Leaderboard 4 data docs0.388
27GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.384
28Claude Opus 4.5claude-opus-4-5-20251101: high-effort· Horangi Korean Leaderboard 4 data docs0.38
29GLM 5 Turboglm-5-turbo· Horangi Korean Leaderboard 4 data docs0.38
30GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.38
31GPT-4.1 minigpt-4.1-mini· Horangi Korean Leaderboard 4 data docs0.38
32Claude Opus 4.1claude-opus-4-1-20250805· Horangi Korean Leaderboard 4 data docs0.37
33GPT-5 minigpt-5-mini-2025-08-07· Horangi Korean Leaderboard 4 data docs0.36
34Claude Sonnet 4.6claude-sonnet-4-6: high-effort· Horangi Korean Leaderboard 4 data docs0.35
35Grok 4.20grok-4.20-beta· Horangi Korean Leaderboard 4 data docs0.35
36Claude Opus 4claude-opus-4-20250514: high-effort· Horangi Korean Leaderboard 4 data docs0.34
37GLM 4.7glm-4.7· Horangi Korean Leaderboard 4 data docs0.34
38GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.34
39Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.34
40Claude Opus 4.8claude-opus-4-8: high-effort· Horangi Korean Leaderboard 4 data docs0.33
41Qwen3.5 27Bqwen3.5-27b· Horangi Korean Leaderboard 4 data docs0.324
42Claude Sonnet 4.5claude-sonnet-4-5-20250929: high-effort· Horangi Korean Leaderboard 4 data docs0.32
43Grok 4 Fastgrok-4-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.32
44DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.3
45GPT 5.4 Nanogpt-5.4-nano-2026-03-17: xhigh-effort· Horangi Korean Leaderboard 4 data docs0.3
46Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.3
47Nemotron 3 Super 120B A12BNVIDIA-Nemotron-3-Super-120B-A12B-FP8· Horangi Korean Leaderboard 4 data docs0.29
48Qwen3.5 122B-A10Bqwen3.5-122b-a10b· Horangi Korean Leaderboard 4 data docs0.29
49Claude Sonnet 5claude-sonnet-5: high-effort· Horangi Korean Leaderboard 4 data docs0.28
50Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507· Horangi Korean Leaderboard 4 data docs0.28

Showing 1–50 of 83 results.

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