# Mathematical Reasoning on OpenR1 Math Evaluation Suite (Math500, AIME24, AMC, Gaokao, Miner., Olymp.) (test)

Source: [Mathematical Reasoning on OpenR1 Math Evaluation Suite (Math500, AIME24, AMC, Gaokao, Miner., Olymp.) (test)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-27T12:58:33.200Z

Evaluation of model performance on the OpenR1 Math Evaluation Suite, covering components like Math500, AIME24, AMC, Gaokao, Miner., and Olympiad subsets, measured on the test split.

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) | OpenR1 Math Evaluation Suite (Math500, AIME24, AMC, Gaokao, Miner., Olymp.) (test) |
| Metric | Math500 Accuracy |
| Unit | PERCENT |
| Direction | Higher 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

- [Math500 Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test.md?metric=Math500%20Accuracy>): Higher is better; unit: PERCENT.

- [AIME24 Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test.md?metric=AIME24%20Accuracy>): Higher is better; unit: PERCENT.

- [AMC Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test.md?metric=AMC%20Accuracy>): Higher is better; unit: PERCENT.

- [Gaokao Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test.md?metric=Gaokao%20Accuracy>): Higher is better; unit: PERCENT.

- [Miner. Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test.md?metric=Miner.%20Accuracy>): Higher is better; unit: PERCENT.

- [Olymp. Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test.md?metric=Olymp.%20Accuracy>): Higher is better; unit: PERCENT.

- [Average Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

- [Rollout Size (M)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-openr1-math-evaluation-suite-math500-aime24-amc-gaokao-miner-olymp-test.md?metric=Rollout%20Size%20(M)>): Higher is better; unit: SIZE.

## Recorded results

| Method | Math500 Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DS | 82.8 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| HIVE | 82.6 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| GRESO | 82.3 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| DS | 77.1 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| HIVE | 76.9 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| GRESO | 76.1 | Not recorded | 69c60eff0636e5bf4afc84e3 |

### DS

Math500 Accuracy: 82.8. Result ID: 69c67e6947f34ce924b07323.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78a81e209131cea79ac6.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Training Data":"OpenR1"}. This record does not assert independent reproduction.

### HIVE

Math500 Accuracy: 82.6. Result ID: 69c67e6947f34ce924b07325.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e3.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Training Data":"OpenR1"}. This record does not assert independent reproduction.

### GRESO

Math500 Accuracy: 82.3. Result ID: 69c67e6947f34ce924b07324.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79181e209131cea7c1cb.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-7B","Training Data":"OpenR1"}. This record does not assert independent reproduction.

### DS

Math500 Accuracy: 77.1. Result ID: 69c67e6947f34ce924b07320.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78a81e209131cea79ac6.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-1.5B","Training Data":"OpenR1"}. This record does not assert independent reproduction.

### HIVE

Math500 Accuracy: 76.9. Result ID: 69c67e6947f34ce924b07322.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e3.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-1.5B","Training Data":"OpenR1"}. This record does not assert independent reproduction.

### GRESO

Math500 Accuracy: 76.1. Result ID: 69c67e6947f34ce924b07321.

[Reporting paper](<https://www.sota2.com/research/paper/69c60eff0636e5bf4afc84e3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79181e209131cea7c1cb.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-Math-1.5B","Training Data":"OpenR1"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
