Video Understanding on Video-MME w/o sub.
76.6AccuracyRETOOL-VIDEO
Evaluation Results
| Method | Links | |
|---|---|---|
| RETOOL-VIDEOSize=9B2026.05 | 76.6 | |
| Claude-Sonnet-4.52026.05 | 75.3 | |
| Gemini 1.5 ProSetting=best-setting numbers from official reports2026.05 | 75 | |
| Gemini-1.5-Pro# Params=-2026.06 | 75 | |
| Gemini-2.5-Flash-Lite2026.05 | 72.7 | |
| GPT-4o2026.05 | 71.9 | |
| GPT-4oSetting=best-setting numbers from official reports2026.05 | 71.9 | |
| GPT-4o# Params=-2026.06 | 71.9 | |
| Gemini-1.5-Flash# Params=-2026.06 | 70.3 | |
| VideoSeek2026.05 | 70.1 | |
| STAR2026.05 | 70 | |
| InternVL3.5-30B-A3BSize=30B2026.05 | 68.7 | |
| DVD2026.05 | 67.3 | |
| GPT-5-Nano-2025-08-072026.05 | 66.2 | |
| NVILASize=8B2026.05 | 64.2 | |
| ParaVT-8BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | 62.1 | |
| Video-Thinker-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | 61.9 | |
| Flash-VStreamSize=7B2026.05 | 61.2 | |
| FramemindSize=7B2026.05 | 60.9 | |
| GPT4-V2026.05 | 60.7 | |
| VILA# Params=40B2026.06 | 60.1 | |
| HYDRA-X# Params=7B2026.06 | 60 | |
| Qwen3-VL-8BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | 59.9 | |
| GPT-4V# Params=-2026.06 | 59.9 | |
| LongVT-RFT-7BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | 59.5 | |
| Time-R1-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | 58.9 | |
| ReWatch-R1-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | 58.8 | |
| VideoRFT-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | 58.5 | |
| VideoMindSize=7B2026.05 | 58.2 | |
| LLaVA-OV# Params=7B2026.06 | 58.2 | |
| Video-R1-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | 57.6 | |
| Show-o2# Params=7B2026.06 | 57.4 | |
| KangarooSize=8B2026.05 | 56 | |
| IXC-2.5# Params=7B2026.06 | 55.8 | |
| Qwen2.5-VL-7BSetting=direct-answer setting (native single-pass prompt)2026.05 | 55.7 | |
| Conan-7BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | 55.5 | |
| VideoThinkerSize=7B2026.05 | 53.7 | |
| LongVA# Params=7B2026.06 | 52.6 | |
| VideoChat-R1-7BSetting=reasoning-enhanced setting (<think>→<answer>)2026.05 | 50.4 | |
| TUNA# Params=1.5B2026.06 | 49.1 | |
| Show-o2# Params=1.5B2026.06 | 48 | |
| VideoLLaMA2# Params=7B2026.06 | 47.9 | |
| VideoLLaMA2Size=8×7B2026.05 | 46.6 | |
| VideoZoomer-7BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | 45.3 | |
| SAGE-7BSetting=tool-augmented setting (<think>→<tool_call>→<answer>)2026.05 | 44.1 | |
| ShareGPT4VideoSize=8B2026.05 | 43.6 |