Visual Question Answering on ViRL39K
50AccuracyThinking model version
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Thinking model versionCategory=Broader STEM Topics, Count=22026.04 | 50 | 514 | 2,904.5 | |
| Thinking model versionCategory=(GradeSchool) Geometric, Count=262026.04 | 34.62 | 233.5 | 3,482.15 | |
| Thinking model versionCategory=Overall, Count=722026.04 | 20.83 | 379.1 | 3,317.29 | |
| Thinking model versionCategory=Spatial Reasoning, Count=62026.04 | 16.67 | 434.5 | 3,398.67 | |
| Thinking model versionCategory=(GradeSchool) Non-Geo Math, Count=212026.04 | 14.29 | 302.19 | 3,640.62 | |
| Thinking model versionCategory=Tables/Diagrams/Charts, Count=122026.04 | 8.33 | 760.83 | 2,097.92 | |
| Thinking model versionCategory=(GradeSchool) Science, Count=32026.04 | 0 | 408.33 | 4,096 | |
| Thinking model versionCategory=Social Science, Count=22026.04 | 0 | 444 | 4,096 |