# Mathematical Reasoning on AMC 23 (Pass@1, TPS, Latency) Source: [Mathematical Reasoning on AMC 23 (Pass@1, TPS, Latency)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:57:24.321Z Evaluation of model performance on the AMC 23 dataset for Mathematical Reasoning tasks, reporting accuracy (Pass@1) alongside throughput (TPS) and latency metrics. 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 | Mathematical Reasoning | | Dataset (including any stated split) | AMC 23 | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Pass@1](): Higher is better; unit: PERCENT. - [TPS](): Higher is better; unit: SCALAR. - [Latency (ms)](): Lower is better; unit: TIME. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | Target Model | 92.5 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | Target Model | 92.5 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | SemanticSpec | 89.2 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | SemanticSpec | 89.2 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | SpecReason | 85.7 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | SpecSampling | 84.2 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | SpecSampling | 82.5 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | SpecReason | 77.5 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | Draft Model | 65.8 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | Draft Model | 65.8 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | SpecThinking | 65 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | | SpecThinking | 61.4 | Not recorded | 6982d2f5a8b01e76cc8e99a0 | ### Target Model Pass@1: 92.5. Result ID: 69964ebb5698665ec4935f14. [Reporting paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction. ### Target Model Pass@1: 92.5. Result ID: 69964ebb5698665ec4935f1a. [Reporting paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction. ### SemanticSpec Pass@1: 89.2. Result ID: 69964ebb5698665ec4935f18. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction. ### SemanticSpec Pass@1: 89.2. Result ID: 69964ebb5698665ec4935f1e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction. ### SpecReason Pass@1: 85.7. Result ID: 69964ebb5698665ec4935f1b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction. ### SpecSampling Pass@1: 84.2. Result ID: 69964ebb5698665ec4935f17. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction. ### SpecSampling Pass@1: 82.5. Result ID: 69964ebb5698665ec4935f1d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction. ### SpecReason Pass@1: 77.5. Result ID: 69964ebb5698665ec4935f15. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction. ### Draft Model Pass@1: 65.8. Result ID: 69964ebb5698665ec4935f13. [Reporting paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction. ### Draft Model Pass@1: 65.8. Result ID: 69964ebb5698665ec4935f19. [Reporting paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction. ### SpecThinking Pass@1: 65. Result ID: 69964ebb5698665ec4935f16. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction. ### SpecThinking Pass@1: 61.4. Result ID: 69964ebb5698665ec4935f1c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.