List your company

Demonstration Selection on Demo-ICL-Bench

76Overall AccuracyHuman
12.0428.64545.2561.855Feb 9, 2026

Evaluation results

MethodLinks
Human2026.027688
Gemini-2.5-Pro2026.0226—
GPT-4o2026.0224.5—
Demo-ICLSize=7B, Frame=322026.022458
Demo-ICL (SFT)Size=7B, Frame=322026.0221.554.5
LLaVA-VideoSize=7B, Frame=322026.0220.544.5
VideoChat-R1Size=7B, Frame=322026.0218.552
Qwen2.5-VLSize=7B, Frame=322026.021846
Qwen2.5-VLSize=72B, Frame=322026.021854
Ola-Video (Base)Size=7B, Frame=322026.021848
Video-R1Size=7B, Frame=322026.0217.548
InternVL-3Size=8B, Frame=322026.0216.544
OlaSize=7B, Frame=322026.021643
Qwen2-VLSize=7B, Frame=322026.0214.538