Video Question Answering on VideoEspresso
83.6AccuracyGemini 2.5 Pro
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 2.5 Pro2026.01 | 83.6 | |
| Qwen2.5-VL-7B+TIR-FlowFrames=322026.01 | 56.3 | |
| LLaVA-onevision-7BFrames=322026.01 | 56.1 | |
| LLaVA-Video-7B+TIR-FlowFrames=322026.01 | 54.2 | |
| Qwen3-VLModel Category=Video MLLMs, Release Date=Oct 252026.04 | 53.7 | |
| AVATARModel Category=Omnimodal MLLMs, Release Date=CVPR 262026.04 | 52.2 | |
| Qwen2-VL-7B-InstructFrames=322026.01 | 52 | |
| Qwen3-OmniModel Category=Omnimodal MLLMs, Release Date=Sep 252026.04 | 51.4 | |
| Omni-o3Model Category=Omnimodal MLLMs2026.04 | 50.9 | |
| Omni-R1Model Category=Omnimodal MLLMs, Release Date=May 252026.04 | 50.4 | |
| VideoChat-R1Model Category=Video MLLMs, Release Date=Apr 252026.04 | 49.4 | |
| EchoInk-R1Model Category=Omnimodal MLLMs, Release Date=May 252026.04 | 49.1 | |
| Open-o3-videoModel Category=Video MLLMs, Release Date=Oct 252026.04 | 48.9 | |
| LLaVA-Video-7BFrames=322026.01 | 48.8 | |
| VideoRFTModel Category=Video MLLMs, Release Date=May 252026.04 | 48.2 | |
| Qwen2.5-VL-7BFrames=322026.01 | 47 | |
| Qwen2.5-OmniModel Category=Omnimodal MLLMs, Release Date=Mar 252026.04 | 46.4 | |
| Qwen2.5-VLModel Category=Video MLLMs, Release Date=Feb 252026.04 | 45.9 | |
| HumanOmniV2Model Category=Omnimodal MLLMs, Release Date=June 252026.04 | 44.4 | |
| Gemini 1.5 ProFrames=1282026.01 | 44.2 | |
| Gemini-1.5-FlashFrames=1282026.01 | 39.8 | |
| AV-ReasonerModel Category=Omnimodal MLLMs, Release Date=June 252026.04 | 35.8 | |
| OlaModel Category=Omnimodal MLLMs, Release Date=Feb 252026.04 | 34.4 | |
| GPT-4oModel Category=Closed-Source APIs, Release Date=May 242026.04 | 26.4 |