K-FinHallu: leaderboard
Large Language Models (LLMs) have advanced financial automation through Retrieval-Augmented Generation (RAG), yet hallucinations remain a critical barrier to deployment in high-stakes environments. Existing benchmarks focus on single-turn, English-centric tasks, leaving the multi-turn dynamics and linguistic-regulatory nuances of the Korean financial domain unaddressed. We introduce K-FinHallu, th
Metric: Accuracy (self-reported). Source: benchmarklist.com. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 86.4 | #245 |
| 2 | Gemini 2.5 Pro | 85.9 | #152 |
| 3 | GPT-5 | 83.3 | #98 |
| 4 | Qwen 3 32B | 77.5 | #443 |
| 5 | Qwen 3 14B | 75.6 | #537 |
| 6 | Llama 3.3 70B | 72.2 | #579 |
| 7 | Qwen 3 8B | 72 | #674 |
| 8 | GPT-4o | 71.5 | #343 |
| 9 | Llama 3.1 70B | 70 | #592 |
| 10 | Llama 3.1 8B | 53.7 | #1151 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=k-finhallu · How It Works · Data refreshed daily, snapshot 2026-10-20.