| title | ObviousBench v0.2.0 Public-Local Release Bundle |
|---|---|
| date | 2026-08-13 |
| type | release-bundle |
| status | local-prep |
This bundle is allowlisted for public review but has not been published. It contains public examples plus the aggregate v0.2 summary CSV and report.
It intentionally excludes private held-out prompts, raw logs, raw model outputs, private review HTML, private item-level outcomes, and private attempt-level outcomes.
- Private held-out items: 144
- Model/config rows: 565
- Complete rows: 565
- Attempt rows: 244080
- Scored attempts: 244080
- Estimated cost: $259.07
configs/registries/model_registry_v1.yamlconfigs/registries/model_thinking_settings_v1.yamldata/public_examples/arithmetic.jsonldata/public_examples/character_count.jsonldata/public_examples/constraint_awareness.jsonldata/public_examples/format_compliance.jsonldata/public_examples/negation.jsonldata/public_examples/ordering.jsonldata/public_examples/spelling_transform.jsonldata/public_examples/word_count.jsonldocs/positioning/background-and-rhetoric.mddocs/reference/benchmark-card.mddocs/reference/methodology.mddocs/reference/scoring-policy.mddocs/reference/source-policy.mddocs/release/v0_2/generated/README.mddocs/release/v0_2/generated/background-and-rhetoric.mddocs/release/v0_2/generated/github-release-notes.mddocs/release/v0_2/generated/huggingface-dataset-card.mddocs/release/v0_2/generated/interactive-results.htmldocs/release/v0_2/generated/launch-essay-draft.mddocs/release/v0_2/generated/model-size-review.csvdocs/release/v0_2/generated/project-page.mddocs/release/v0_2/generated/provenance.jsondocs/release/v0_2/generated/public-release-checklist.mddocs/release/v0_2/generated/release-metadata.jsondocs/release/v0_2/generated/social-snippets.mdreports/v0_2/aggregate/report.mdreports/v0_2/aggregate/summary.csv