Visual Question Answering on PuzzleVQA
61AccuracyOctoTools
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| OctoToolsBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=false, Multi-step Reasoning=true2025.02 | 61 | 8.8 | 7 | |
| OctoToolsbaseBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=false, Multi-step Reasoning=true2025.02 | 59.3 | — | — | |
| CoTBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=false, Multi-step Reasoning=true2025.02 | 54 | — | — | |
| 0-shotBackbone=gpt-4o-2024-08-06, Modality=Vision, Domain=General, Visual Understanding=true, Numerical Calculation=false, Knowledge Retrieval=false, Multi-step Reasoning=true2025.02 | 52.2 | — | — |