# Process Verification on ProcessBench With Standard Answers Source: [Process Verification on ProcessBench With Standard Answers]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:58:11.414Z Evaluation of model performance on the Process Verification task using the ProcessBench With Standard Answers dataset, utilizing various accuracy and F1 metrics (Precise, Absolute, Approximate, Rough). 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 | Process Verification | | Dataset (including any stated split) | ProcessBench With Standard Answers | | Metric | Precise Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Precise Accuracy](): Higher is better; unit: PERCENT. - [Abs. Accuracy](): Higher is better; unit: PERCENT. - [Precise F1](): Higher is better; unit: PERCENT. - [Abs. F1](): Higher is better; unit: PERCENT. - [Approximate Accuracy](): Higher is better; unit: PERCENT. - [Approximate F1](): Higher is better; unit: PERCENT. - [Rough Accuracy](): Higher is better; unit: PERCENT. - [Rough F1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Precise Accuracy | Result date | Report paper | | --- | --- | --- | --- | | OPV-32B | 78.9 | Not recorded | 693ba1796cfd488761a55186 | | OPV-Stage2 | 71.6 | Not recorded | 693ba1796cfd488761a55186 | | R1-Distill-Qwen-32B | 70.5 | Not recorded | 693ba1796cfd488761a55186 | | OPV-Stage1 | 68.8 | Not recorded | 693ba1796cfd488761a55186 | | Qwen3-32B | 68 | Not recorded | 693ba1796cfd488761a55186 | | DeepSeek-V3-0324 | 67.9 | Not recorded | 693ba1796cfd488761a55186 | | DeepSeek-R1-0528 | 67 | Not recorded | 693ba1796cfd488761a55186 | | Qwen3-Max-Preview | 66.4 | Not recorded | 693ba1796cfd488761a55186 | | QwQ-32B | 65.2 | Not recorded | 693ba1796cfd488761a55186 | | gpt-oss-120b (high) | 61 | Not recorded | 693ba1796cfd488761a55186 | | Qwen2.5-Math-PRM-72B | 55.4 | Not recorded | 693ba1796cfd488761a55186 | | gpt-oss-120b (high) | 0.833 | Not recorded | 693ba1796cfd488761a55186 | | Qwen3-Max-Preview | 0.832 | Not recorded | 693ba1796cfd488761a55186 | | DeepSeek-R1-0528 | 0.822 | Not recorded | 693ba1796cfd488761a55186 | | OPV-32B | 0.801 | Not recorded | 693ba1796cfd488761a55186 | | Qwen2.5-Math-PRM-72B | 0.772 | Not recorded | 693ba1796cfd488761a55186 | | DeepSeek-V3-0324 | 0.745 | Not recorded | 693ba1796cfd488761a55186 | | R1-Distill-Qwen-32B | 0.647 | Not recorded | 693ba1796cfd488761a55186 | ### OPV-32B Precise Accuracy: 78.9. Result ID: 6996c36f5698665ec40ec525. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### OPV-Stage2 Precise Accuracy: 71.6. Result ID: 6996c36f5698665ec40ec524. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### R1-Distill-Qwen-32B Precise Accuracy: 70.5. Result ID: 6996c36f5698665ec40ec522. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### OPV-Stage1 Precise Accuracy: 68.8. Result ID: 6996c36f5698665ec40ec523. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### Qwen3-32B Precise Accuracy: 68. Result ID: 6996c36f5698665ec40ec51b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### DeepSeek-V3-0324 Precise Accuracy: 67.9. Result ID: 6996c36f5698665ec40ec51d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### DeepSeek-R1-0528 Precise Accuracy: 67. Result ID: 6996c36f5698665ec40ec51e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### Qwen3-Max-Preview Precise Accuracy: 66.4. Result ID: 6996c36f5698665ec40ec51f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### QwQ-32B Precise Accuracy: 65.2. Result ID: 6996c36f5698665ec40ec51c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### gpt-oss-120b (high) Precise Accuracy: 61. Result ID: 6996c36f5698665ec40ec520. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### Qwen2.5-Math-PRM-72B Precise Accuracy: 55.4. Result ID: 6996c36f5698665ec40ec521. [Reporting paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### gpt-oss-120b (high) Precise Accuracy: 0.833. Result ID: 6996c36f5698665ec40ec510. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### Qwen3-Max-Preview Precise Accuracy: 0.832. Result ID: 6996c36f5698665ec40ec50d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### DeepSeek-R1-0528 Precise Accuracy: 0.822. Result ID: 6996c36f5698665ec40ec50f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### OPV-32B Precise Accuracy: 0.801. Result ID: 6996c36f5698665ec40ec513. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### Qwen2.5-Math-PRM-72B Precise Accuracy: 0.772. Result ID: 6996c36f5698665ec40ec511. [Reporting paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### DeepSeek-V3-0324 Precise Accuracy: 0.745. Result ID: 6996c36f5698665ec40ec50e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. ### R1-Distill-Qwen-32B Precise Accuracy: 0.647. Result ID: 6996c36f5698665ec40ec512. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Voting":"maj@8"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.