| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Question Answering | CORTEXBENCH Comparison | Accuracy95.7 | 32 | |
| Question Answering | CORTEXBENCH Bridge | Accuracy96.1 | 32 | |
| Robot Learning | CortexBench | Adroit Score74.7 | 22 | |
| Evidence Retrieval | CORTEXBENCH Comparison | Hit@546 | 8 | |
| Evidence Retrieval | CORTEXBENCH Bridge | Hit@538.4 | 8 | |
| Object Navigation | CortexBench ObjNav | Success80 | 3 |