VANTAGE-Bench - Temporal: leaderboard
VANTAGE-Bench vision-language video-understanding leaderboard — temporal accuracy.
Metric: Temporal (%). Source: huggingface.co. Saturation forecast: Around 2029. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 51.64 | #6 |
| 2 | GPT-5.6 Sol | 46.5 | #19 |
| 3 | Gemini 3.6 Flash | 43.83 | #51 |
| 4 | Gemini 3.1 Pro (Preview) | 40.62 | #58 |
| 5 | Qwen 3 VL 32B Instruct | 38.1 | #283 |
| 6 | Qwen 3 VL 8B Instruct | 36.98 | #420 |
| 7 | Qwen 3.5 9B | 35.2 | #379 |
| 8 | Gemini 3.1 Flash Lite | 35.13 | #191 |
| 9 | Qwen 3.5 27B | 31.93 | #187 |
| 10 | Gemini 3.5 Flash Lite | 28.14 | #156 |
| 11 | Gemma 4 E2B (IT) | 9.08 | #781 |
No result here: #3 Claude Opus 5.5, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=vantage-bench-temporal · How It Works · Data refreshed daily, snapshot 2026-10-20.