# Intermediate Answer Generation Latency on MATH Source: [Intermediate Answer Generation Latency on MATH]() Collection index: [llms.txt]() Data updated: 2026-03-05T07:28:40.532Z Evaluation of model performance on generating intermediate answers for mathematical problems sourced from the MATH dataset, specifically measuring the average time taken for generation. 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 | Intermediate answer generation | | Dataset (including any stated split) | MATH | | Metric | Average Latency (s) | | Unit | TIME | | Direction | Lower is better | | Results loaded | 6 of 6 | | 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 - [Average Latency (s)](): Lower is better; unit: TIME. ## Recorded results | Method | Average Latency (s) | Result date | Report paper | | --- | --- | --- | --- | | MSVN | 0.7 | Not recorded | 69a90de32d603e6de3e40602 | | MSVN | 0.7 | Not recorded | 69a90de32d603e6de3e40602 | | Probe | 0.9 | Not recorded | 69a90de32d603e6de3e40602 | | Probe | 1.9 | Not recorded | 69a90de32d603e6de3e40602 | | MSVN | 2.1 | Not recorded | 69a90de32d603e6de3e40602 | | Probe | 6.2 | Not recorded | 69a90de32d603e6de3e40602 | ### MSVN Average Latency (s): 0.7. Result ID: 69a9309b6dbb7075b95232f1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"4"}. This record does not assert independent reproduction. ### MSVN Average Latency (s): 0.7. Result ID: 69a9309b6dbb7075b95232f3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"16"}. This record does not assert independent reproduction. ### Probe Average Latency (s): 0.9. Result ID: 69a9309b6dbb7075b95232f0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"4"}. This record does not assert independent reproduction. ### Probe Average Latency (s): 1.9. Result ID: 69a9309b6dbb7075b95232f2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"16"}. This record does not assert independent reproduction. ### MSVN Average Latency (s): 2.1. Result ID: 69a9309b6dbb7075b95232f5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"64"}. This record does not assert independent reproduction. ### Probe Average Latency (s): 6.2. Result ID: 69a9309b6dbb7075b95232f4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"N":"64"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.