EVID-Bench - Synthetic Insertion: leaderboard
Metric: Point-level accuracy (%) on the 24 synthetic insertion videos (AI generation: a generated clip inserted into real footage), using the retrieval-augmented verification pipeline of the paper (chain-of-thought analysis, up to six YouTube search-verify-reflect rounds, 64 frames at 480p, temperature 0); each video has 3 to 5 annotated misinformation points, matched by a majority of three LLM judges; mean of three runs; higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 16.67 |
| 2 | Gemini 3.1 Pro (Preview) | 13.9 |
| 3 | Qwen 3.5 Plus | 13.9 |
| 4 | Claude Opus 4.6 | 13.89 |
| 5 | Claude Sonnet 4.6 | 12.5 |
| 6 | Qwen 3 VL 235B A22B Instruct | 12.5 |
| 7 | Gemini 3 Flash | 11.1 |
| 8 | GPT-5.4 | 9.72 |
| 9 | GPT-5.4 Mini | 6.94 |
Interactive version: theaggregate.ai/benchmark?slug=evid-bench-synthetic-insertion · How It Works · Data refreshed daily, snapshot 2026-09-29.