EG-VQA - Counterfactual: leaderboard
Strict answer accuracy of EG-VQA (2026) on counterfactual questions (outcomes of a hypothetical change). EG-VQA (2026) asks open-ended questions about activity, instructional and cooking videos and grades answers with an LLM judge; accuracy in percent, higher is better.
Metric: Strict accuracy (%) on counterfactual questions (outcomes of a hypothetical change), on the 2,889-question EG-VQA test split (open-ended questions over ActivityNet Captions, HiREST and YouCook2 videos, 64 uniformly sampled frames), answers graded by a Gemini-2.5-Pro judge against the reference answer; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4o | 35.1 | #741 |
| 2 | Gemini 2.5 Flash | 28.89 | #453 |
| 3 | Qwen 2.5 VL 7B Instruct | 16.8 | #1833 |
| 4 | InternVL3-8B | 13.64 | #1688 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=eg-vqa-counterfactual · How It Works · Data refreshed daily, snapshot 2026-11-13.