Artifact-Bench (AI-Generated Video): leaderboard
Metric: Overall accuracy (%) over all 1,100 questions of the three tasks (500 real vs AI-generated classification, 250 pairwise realism comparison, 350 artifact identification), 1,100 manually annotated questions on 1,350 real and AI-generated videos from seven generators, at 5 fps frame sampling, each model at its officially recommended decoding (Gemini 3.1 Pro at temperature 1.0 and high thinking level) or greedy, answers parsed by Gemini 3.1 Pro; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 47.5 |
| 2 | Gemini 3 Flash | 43.8 |
| 3 | Qwen 3 VL 32B Instruct | 39.5 |
| 4 | Qwen 3 VL 32B (Thinking) | 37.3 |
| 5 | Qwen 3 VL 30B A3B (Thinking) | 36.3 |
| 6 | Qwen 3 VL 8B Instruct | 36 |
| 7 | Qwen 3 VL 30B A3B Instruct | 35.5 |
| 8 | Molmo2-8B | 34.5 |
| 9 | Qwen 3 VL 8B (Thinking) | 33.3 |
Interactive version: theaggregate.ai/benchmark?slug=artifact-bench-ai-generated-video · How It Works · Data refreshed daily, snapshot 2026-10-07.