KOFFVQA - Hallucination and Robustness — leaderboard
Metric: Score (%). Source: huggingface.co. 82 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 Mini | 90 |
| 2 | Llama 4 Scout Instruct | 90 |
| 3 | Gemini 2.5 Flash (Preview 04-17) | 90 |
| 4 | InternVL3-38B | 86 |
| 5 | Qwen 2.5 VL 32B Instruct | 86 |
| 6 | InternVL2.5-78B | 85 |
| 7 | InternVL3-78B | 80 |
| 8 | Claude 3.5 Sonnet (20241022) | 80 |
| 9 | Ovis2-8B | 80 |
| 10 | GPT-4.1 | 80 |
| 11 | Mistral Small 3.1 | 80 |
| 12 | O4 Mini (2025-04-16) | 80 |
| 13 | GPT-4 Turbo | 80 |
| 14 | O3 (2025-04-16) | 80 |
| 15 | O1 (2024-12-17) | 80 |
Interactive version: theaggregate.ai/benchmark?slug=koffvqa-hallucination-and-robustness · How the rankings work · Data refreshed daily, snapshot 2026-07-22.