TAR-Bench: leaderboard
Metric: Mean score (%; unweighted mean of the ten task scores: accuracy for binary and multiple-choice QA, mean IoU for temporal localization, scaled BERTScore F1 for the seven open-ended tasks; zero-shot in non-reasoning (direct-answer) mode through VLMEvalKit, mean of 3 runs, on TAR-Bench: 960 human-curated annotations for 80 held-out traffic-anomaly clips from 17 public YouTube videos). Source: arxiv.org. Saturation forecast: Around 2034. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 27B (Non-reasoning) | 39.5 |
| 2 | Qwen 3.5 9B (Non-reasoning) | 39.1 |
| 3 | Gemini 3.1 Pro (Preview) | 36.3 |
| 4 | Gemma 4 31B (IT) | 33.3 |
| 5 | Qwen 3 VL 8B Instruct | 30.9 |
| 6 | Qwen 3 VL 32B Instruct | 28 |
Interactive version: theaggregate.ai/benchmark?slug=tar-bench · How It Works · Data refreshed daily, snapshot 2026-09-29.