LiveCodeBench — Shared Historical Cohort
Lumina VerifiedLumina checked the published sources, versions, model labels, score extraction and conversion. External evaluations were run by their publishers; Lumina has not independently rerun or reproduced them.Pass@1
LiveCodeBench — Shared Historical Cohort
No comparable per-task resource measurements were published. Missing metrics are omitted from their graph; quality scores remain available.
Results table
Method & coverage
Original 28-model generation export with exactly the same 1,055 questions for every model. Arithmetic mean of published per-question pass@1, no grading changes or mixed question windows. Historical cohort retained as complementary evidence, not current-generation evidence.
No comparable per-task resource measurements were published.
How the Lumina conversion works
1,000 + 75 × ((original score − 68.99813811780636) / 17.547837799039314). The result is rounded once. Scores may tie.
Frozen initial observed text-only cohort; one mean per exact publisher release/API, balancing repeated settings/routes within that release. Original score and protocol remain separate. No inferred variants or future refitting.
- Calibration
- livecodebench-historical-z75-v1 · experimental
- Reference mean
- 68.99813811780636
- Population SD
- 17.547837799039314
- Coverage
- Standalone benchmark.
Identity, exclusions & attribution
Original measurements and exact source settings retained; unknown API, effort and harness versions remain unknown.
Text programming problem statements and code test results.
Standalone text benchmark; no new combined index. Source identity/effort/protocol qualifications remain in Data and CSV.
All published reasoning settings, including Claude Max, are included by default. Display labels use Low and xHigh; source labels remain in the retained records.
Publisher terms. Scores and resource figures are attributed to the original publisher.