RankingDataset
UnifyBench dataset
Download the benchmark data (JSON). Published observations used to build the scores. Calculation details on methodology.
The download includes launch-page observations, exact reported configurations, source locators and metric units. Launch review dates are labeled separately from evaluation dates. Compare the published evidence.
Download effort-specific benchmark measurements or compare effort levels. The configuration leaderboard uses this dated collection alongside admitted catalog observations; save both downloads when citing a ranking.
Check each ranking collection’s review date. A successful refresh publishes validated benchmark changes together. New models, settings and unsupported source changes require review; failed checks retain the last accepted evidence.
Download dated pricing and workload costs or inspect Value coverage. Prices are separate from quality scoring; missing costs never remove Capability eligibility.
Download reported effort settings for every model and observation. Unspecified settings remain unknown.
Inspect every collected observation and its admission decision. The effort pages explain source concentration and score sensitivity for the selected configuration.
Download the capability registry, fixed reference panel and scoring rules. Reproduction also requires the scoring version, evidence policy and selected capability weights.
Download the dated configuration audit: held-out predictions, alternative weighting schemes, source sensitivity and coverage gaps. The published audit identifies the exact scoring inputs used by this release.
Download this dated release. This URL preserves these scores for citation.
Archive this ranking's evidence
Save these permanent links with your citation. They retain the published inputs, configuration outputs and validation when the current datasets change. Historical scoring implementation code is not included in these downloads.
Reuse and attribution
You may reuse UnifyBench's original aggregate results with credit to UnifyBench and a link to the dated data release.
This permission does not cover upstream benchmark data or source material, which remain subject to their own terms.
Publisher and corrections
Published and maintained by Mustafa "Moes" Mufti.
For corrections, email m.mufti@m-finance.io. Include the model, exact setting, benchmark and original source link.