OmniCompass-AV - Spatial Grounding - Consistency Score: leaderboard

OmniCompass-AV - Spatial Grounding - Consistency Score. Matched text-only/text-plus-image target specifications; consistency requires both target forms correct. 240 audiovisual videos, 720 task instances. Source-specific frame budgets retained in primary table; no fusion with single-condition accuracy. Metric: Consistency score (%). Primary published table; source configurations remain distinct.

Metric: Consistency score (%). Source: arxiv.org. Saturation forecast: Around January 2027. 17 models tracked.

Top models

#ModelScoreOverall rank
1Gemini 3.8 Flash53.5#21
2Qwen3.8 Omni Flash50.9#29
3Qwen 3.5 Omni Plus50.5#82
4Gemini 3.1 Pro (Preview)45.8#56
5Qwen3.5 Omni Flash34.7#173
6MiMo-V2.523.4#192
7Qwen2.5-Omni-7B7#608

No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.

Interactive version: theaggregate.ai/benchmark?slug=omnicompass-av-spatial-grounding-consistency-score · How It Works · Data refreshed daily, snapshot 2026-10-16.