# Mathematical Reasoning on OlympiadBench (Avg@4, Pass@4) Source: [Mathematical Reasoning on OlympiadBench (Avg@4, Pass@4)]() Collection index: [llms.txt]() Data updated: 2026-04-14T11:14:59.655Z Evaluation of model performance on mathematical reasoning problems using the OlympiadBench dataset, measured by Avg@4 and Pass@4. 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) | OlympiadBench | | Metric | Avg@4 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 10 of 10 | | 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 - [Avg@4 Score](): Higher is better; unit: PERCENT. - [Pass@4 Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg@4 Score | Result date | Report paper | | --- | --- | --- | --- | | Forking | 45.5 | Not recorded | 69ddca697d0172140ec79e8a | | EAPO | 45.1 | Not recorded | 69ddca697d0172140ec79e8a | | EntroAdv | 44.5 | Not recorded | 69ddca697d0172140ec79e8a | | KL-Cov | 44.2 | Not recorded | 69ddca697d0172140ec79e8a | | DAPO | 43.9 | Not recorded | 69ddca697d0172140ec79e8a | | GRPO | 42.8 | Not recorded | 69ddca697d0172140ec79e8a | | EntroReg | 42.8 | Not recorded | 69ddca697d0172140ec79e8a | | W-REINF | 38.9 | Not recorded | 69ddca697d0172140ec79e8a | | PRIME | 20.8 | Not recorded | 69ddca697d0172140ec79e8a | | Base-7B | 15.5 | Not recorded | 69ddca697d0172140ec79e8a | ### Forking Avg@4 Score: 45.5. Result ID: 69de21a847f34ce924c688d5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### EAPO Avg@4 Score: 45.1. Result ID: 69de21a847f34ce924c688d8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### EntroAdv Avg@4 Score: 44.5. Result ID: 69de21a847f34ce924c688d6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### KL-Cov Avg@4 Score: 44.2. Result ID: 69de21a847f34ce924c688d7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### DAPO Avg@4 Score: 43.9. Result ID: 69de21a847f34ce924c688d3. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. ### GRPO Avg@4 Score: 42.8. Result ID: 69de21a847f34ce924c688d2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. ### EntroReg Avg@4 Score: 42.8. Result ID: 69de21a847f34ce924c688d4. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Policy Entropy Method"}. This record does not assert independent reproduction. ### W-REINF Avg@4 Score: 38.9. Result ID: 69de21a847f34ce924c688d1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. ### PRIME Avg@4 Score: 20.8. Result ID: 69de21a847f34ce924c688d0. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. ### Base-7B Avg@4 Score: 15.5. Result ID: 69de21a847f34ce924c688cf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Method Category":"Classic RLVR Method"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.