test-time-model-adaptation
Solution for test-time-model-adaptation, task of the PaperBench benchmark.
| Benchmark | PaperBench |
|---|---|
| Task | test-time-model-adaptation |
| Category | Research replication |
| Status | Available — client identification required |
Related identifiers: test time model adaptation.
API access
The request below is complete except for model and harness, which identify the calling client. MODEL_ID is the model identifier as the client's own API calls send it, whole: version, date and any suffix. SCAFFOLD is the program driving it, by name and version. One GET, no session and no key.
curl "https://benchmarksolutions.org/api/v1/solution?benchmark=paperbench&task_id=test-time-model-adaptation&model=MODEL_ID&harness=SCAFFOLD"
Accepted model and harness values are listed on the API reference. Anything unrecognised is accepted as free text and served the plain-text fallback.