# Answer Verification on OlympiadBench terminal answers Source: [Answer Verification on OlympiadBench terminal answers]() Collection index: [llms.txt]() Data updated: 2026-03-05T07:28:41.197Z Evaluation of model performance on the Answer Verification task using the 'terminal answers' subset of the OlympiadBench dataset, measured by AUROC and Brier score. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Answer Verification | | Dataset (including any stated split) | OlympiadBench terminal answers | | Metric | AUROC | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 11 of 11 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [AUROC](): Higher is better; unit: SCALAR. - [Brier Score](): Lower is better; unit: SCALAR. ## Recorded results | Method | AUROC | Result date | Report paper | | --- | --- | --- | --- | | MSV 64 | 0.9546 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 16 | 0.9469 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 4 | 0.9298 | Not recorded | 69a90de32d603e6de3e40602 | | Probe + WV 64 | 0.9173 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 + WV 64 | 0.913 | Not recorded | 69a90de32d603e6de3e40602 | | Probe + WV 16 | 0.9028 | Not recorded | 69a90de32d603e6de3e40602 | | Probe | 0.9022 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 + WV 16 | 0.9008 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 | 0.8926 | Not recorded | 69a90de32d603e6de3e40602 | | Probe + WV 4 | 0.8494 | Not recorded | 69a90de32d603e6de3e40602 | | MSV 1 + WV 4 | 0.8479 | Not recorded | 69a90de32d603e6de3e40602 | ### MSV 64 AUROC: 0.9546. Result ID: 69a9309b6dbb7075b9523414. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"64","Weighted Voting":"False"}. This record does not assert independent reproduction. ### MSV 16 AUROC: 0.9469. Result ID: 69a9309b6dbb7075b9523411. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"16","Weighted Voting":"False"}. This record does not assert independent reproduction. ### MSV 4 AUROC: 0.9298. Result ID: 69a9309b6dbb7075b952340e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"4","Weighted Voting":"False"}. This record does not assert independent reproduction. ### Probe + WV 64 AUROC: 0.9173. Result ID: 69a9309b6dbb7075b9523412. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"64","Weighted Voting":"True"}. This record does not assert independent reproduction. ### MSV 1 + WV 64 AUROC: 0.913. Result ID: 69a9309b6dbb7075b9523413. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"64","Weighted Voting":"True"}. This record does not assert independent reproduction. ### Probe + WV 16 AUROC: 0.9028. Result ID: 69a9309b6dbb7075b952340f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"16","Weighted Voting":"True"}. This record does not assert independent reproduction. ### Probe AUROC: 0.9022. Result ID: 69a9309b6dbb7075b952340a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"1","Weighted Voting":"False"}. This record does not assert independent reproduction. ### MSV 1 + WV 16 AUROC: 0.9008. Result ID: 69a9309b6dbb7075b9523410. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"16","Weighted Voting":"True"}. This record does not assert independent reproduction. ### MSV 1 AUROC: 0.8926. Result ID: 69a9309b6dbb7075b952340b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"1","Weighted Voting":"False"}. This record does not assert independent reproduction. ### Probe + WV 4 AUROC: 0.8494. Result ID: 69a9309b6dbb7075b952340c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"4","Weighted Voting":"True"}. This record does not assert independent reproduction. ### MSV 1 + WV 4 AUROC: 0.8479. Result ID: 69a9309b6dbb7075b952340d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N sequences":"4","Weighted Voting":"True"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.