List your company

Visual Question Answering on TQA

77.5AccuracySPECTRA
17.733.22548.7564.275Apr 19, 2026

Evaluation results

MethodLinks
SPECTRAAgency Type (Agentic vs Non-Agentic)=Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Qwen2.5-VL, Model Scale (Parameters)=7B, Framework=VERL2026.0477.5
GPT-4oAgency Type (Agentic vs Non-Agentic)=Non-Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=GPT-4o2026.0477
Qwen2.5-VLAgency Type (Agentic vs Non-Agentic)=Non-Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Qwen2.5-VL, Model Scale (Parameters)=7B2026.0474.6
GPT-4o MiniAgency Type (Agentic vs Non-Agentic)=Non-Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=GPT-4o Mini2026.0473.5
VERLAgency Type (Agentic vs Non-Agentic)=Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Qwen2.5-VL, Model Scale (Parameters)=7B, Framework=VERL2026.0473.3
Gemma-3-ITAgency Type (Agentic vs Non-Agentic)=Non-Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Gemma-3-IT, Model Scale (Parameters)=4B2026.0473
HF SmolAgentAgency Type (Agentic vs Non-Agentic)=Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Qwen2.5-VL, Model Scale (Parameters)=7B, Framework=HF SmolAgent2026.0472.5
CustomAgency Type (Agentic vs Non-Agentic)=Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Gemma-3-IT, Model Scale (Parameters)=4B, Framework=Custom2026.0468
SPECTRAAgency Type (Agentic vs Non-Agentic)=Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Qwen2.5-VL, Model Scale (Parameters)=3B, Framework=VERL2026.0460
VERLAgency Type (Agentic vs Non-Agentic)=Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Qwen2.5-VL, Model Scale (Parameters)=3B, Framework=VERL2026.0456
Phi-4-MultimodalAgency Type (Agentic vs Non-Agentic)=Non-Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Phi-4-Multimodal, Model Scale (Parameters)=6B2026.0452
Qwen2.5-VLAgency Type (Agentic vs Non-Agentic)=Non-Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Qwen2.5-VL, Model Scale (Parameters)=3B2026.0442.2
CustomAgency Type (Agentic vs Non-Agentic)=Agentic, Evaluation Protocol (Zero-shot)=Zero-shot, Backbone Architecture=Phi-4-Multimodal, Model Scale (Parameters)=6B, Framework=Custom2026.0420