VANTAGE-Bench - Event Verification: leaderboard

VANTAGE-Bench vision-language video-understanding leaderboard — event-verification accuracy.

Metric: Event Verification (%). Source: huggingface.co. Saturation forecast: Around January 2027. 18 models tracked.

Top models

#ModelScoreOverall rank
1GPT-6 Astra86.9#6
2Gemini 3.6 Flash82#51
3GPT-5.6 Sol76.14#19
4Gemini 3.5 Flash Lite70.41#156
5Gemini 3.1 Pro (Preview)68.57#58
6Gemini 3.1 Flash Lite63.78#191
7Qwen 3 VL 32B Instruct60.04#283
8Qwen 3 VL 8B Instruct59.39#420
9Qwen 3.5 27B55.34#187
10Qwen 3.5 9B46.78#379
11Gemma 4 E2B (IT)27.65#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-event-verification · How It Works · Data refreshed daily, snapshot 2026-10-20.