Artifact-Bench (AI-Generated Video) - Real vs AI-Generated Classification: leaderboard
Artifact-Bench (2026) tests whether multimodal LLMs perceive the artifacts of AI-generated videos, on 1,100 manually annotated questions over real videos and clips from seven video generators, split into three difficulty levels. This task asks whether a single video is real or AI-generated; accuracy is the mean of the three difficulty levels, in percent, higher is better.
Metric: Accuracy (%) on the 500 binary real versus AI-generated video questions (RVAC), the unweighted mean of the three difficulty levels, 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 February 2027. 19 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 74 | #102 |
| 2 | VideoVeritas-8B | 68.2 | |
| 3 | Gemini 3 Flash | 64.7 | #180 |
| 4 | Qwen 3 VL 32B Instruct | 53.5 | #607 |
| 5 | BusterX++ 7B | 52 | |
| 6 | Skyra-7B-RL | 51.4 | |
| 7 | Qwen 3 VL 32B (Thinking) | 50.9 | #577 |
| 8 | MiMo-VL-7B-RL | 50 | #1160 |
| 9 | MiMo-VL-7B-SFT | 49.7 | #1097 |
| 10 | Qwen 3 VL 8B Instruct | 49.6 | #1043 |
| 11 | Qwen 3 VL 30B A3B (Thinking) | 49.3 | #727 |
| 12 | Skyra-7B-SFT | 49.2 | |
| 13 | Qwen 3 VL 30B A3B Instruct | 48.9 | #903 |
| 14 | Qwen 3 VL 8B (Thinking) | 48.8 | #924 |
| 15 | Keye-VL-1.5-8B | 48.7 | #1729 |
No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=artifact-bench-ai-generated-video-real-vs-ai-generated-classification · How It Works · Data refreshed daily, snapshot 2026-11-22.