Information Seeking on InfoSeek
66.45ScoreGemini-3-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemini-3-ProWorkflow=Agentic Model, Zero-shot=true2026.07 | 66.45 | |
| GPT-5.2Workflow=Agentic Model, Zero-shot=true2026.07 | 65.55 | |
| Gemini-3-FlashWorkflow=Agentic Model, Zero-shot=true2026.07 | 61.1 | |
| GPT-4oWorkflow=Agentic Model, Zero-shot=true2026.07 | 59.55 | |
| VideoSearcher-8BWorkflow=Agentic Model, Zero-shot=false2026.07 | 58.3 | |
| Webwatcher-7BWorkflow=Agentic Model, Zero-shot=false2026.07 | 56.9 | |
| Gemini-3-ProWorkflow=Direct Answer, Zero-shot=false2026.07 | 56.3 | |
| MMSearch-R1Workflow=Agentic Model, Zero-shot=false2026.07 | 55.1 | |
| Gemini-3-FlashWorkflow=Direct Answer, Zero-shot=false2026.07 | 54.85 | |
| GPT-4oWorkflow=Direct Answer, Zero-shot=false2026.07 | 52.9 | |
| DeepEyesV2Workflow=Agentic Model, Zero-shot=false2026.07 | 51.1 | |
| GPT-5.2Workflow=Direct Answer, Zero-shot=false2026.07 | 50.4 | |
| Qwen2.5-VL-32B-InstructWorkflow=Agentic Model, Zero-shot=true2026.07 | 50.1 | |
| Qwen3-VL-32B-InstructWorkflow=Agentic Model, Zero-shot=true2026.07 | 49.85 | |
| VideoSearcher-4BWorkflow=Agentic Model, Zero-shot=false2026.07 | 49.25 | |
| Qwen3-VL-8B-InstructWorkflow=Agentic Model, Zero-shot=true2026.07 | 46.15 | |
| Visual-ARFTWorkflow=Agentic Model, Zero-shot=false2026.07 | 37.95 | |
| Qwen2.5-VL-32B-InstructWorkflow=Direct Answer, Zero-shot=false2026.07 | 36.65 | |
| Qwen2.5-VL-7B-InstructWorkflow=Direct Answer, Zero-shot=false2026.07 | 31.95 | |
| Qwen3-VL-32B-InstructWorkflow=Direct Answer, Zero-shot=false2026.07 | 28.95 | |
| Qwen2.5-VL-7B-InstructWorkflow=Agentic Model, Zero-shot=true2026.07 | 28.8 | |
| Qwen3-VL-4B-InstructWorkflow=Agentic Model, Zero-shot=true2026.07 | 28.1 | |
| Qwen3-VL-4B-InstructWorkflow=Direct Answer, Zero-shot=false2026.07 | 25.75 | |
| Qwen3-VL-8B-InstructWorkflow=Direct Answer, Zero-shot=false2026.07 | 23.15 |