K-FinHallu - Hallucination Type Classification: leaderboard

Macro-F1 (0-100) at naming the type of a hallucinated response (contradictory, unverifiable, irrelevant, false acceptance or false refusal) in K-FinHallu (2026), a benchmark of multi-turn Korean financial RAG dialogues built from public financial documents, with injected hallucinations and refusal cases. Higher is better.

Metric: Macro-F1 (0-100) over five hallucination types (contradictory, unverifiable, irrelevance, false acceptance, false refusal) on the 404 hallucinated test responses, multi-turn Korean financial RAG dialogues, temperature 0 where applicable; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemini 2.5 Pro72.5#276
2GPT-571.7#178
3Gemini 2.5 Flash66.9#463
4Qwen 3 32B49.2#972
5Qwen 3 14B44.2#1269
6Qwen 3 8B38.7#1873
7GPT-4o28.9#751
8Llama 3.1 70B13.3#1499
9Llama 3.3 70B10.3#1514
10Llama 3.1 8B8.7#5196
11EXAONE 4.0 32B3.9#1398
12kanana-2-30B-a3B-instruct2.2

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=k-finhallu-hallucination-type-classification · How It Works · Data refreshed daily, snapshot 2026-11-21.