nano-gpt-data-curation
gpt-5.6-sol
nano-gpt-data-curation — graded by the task's verifier against a measured baseline.
- backend
- modal
- variant
- codex azure_ai/gpt-5.6-sol
- metric
- held-out multi-domain perplexity
- actions
- 58
- duration
- 19m
- recorded
- 2026-08-03
run iddclm-nano-curation__JnvJaaT
What the verifier emitted for this run, as recorded. The fields differ by task family — the task’s verification method explains what they mean.
- score
- 404.83
- metric
- held-out multi-domain perplexity
- direction
- lower_better
- baseline
- 426.38
- theoretical best
- 1
- practical best
- 1
- status
- ok
- flags
- none
- reward
- 404.83
- metrics
- held-out perplexity
- 404.83
- floor ppl
- 426.38