OmniCapBench - EVSA F1: leaderboard
Metric: EVSA F1 (%; structured audio-visual captioning, native atomic evaluation). Source: 01yzzyu.github.io. Saturation forecast: Around August 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 51.46 |
| 2 | Gemini 2.5 Pro | 43.74 |
| 3 | Qwen 3.5 Omni Plus | 40.2 |
| 4 | Qwen3.5 Omni Flash | 35.58 |
Interactive version: theaggregate.ai/benchmark?slug=omnicapbench-evsa-f1 · How It Works · Data refreshed daily, snapshot 2026-10-10.