# Mathematical Reasoning on Math500, AIME24, AMC, Gaokao, Minerva Math, and Olympiad Bench

Source: [Mathematical Reasoning on Math500, AIME24, AMC, Gaokao, Minerva Math, and Olympiad Bench](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-aime24-amc-gaokao-minerva-math-and-olympiad-bench>)

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

Data updated: 2026-03-27T12:58:33.160Z

Evaluation of Mathematical Reasoning performance across a custom suite comprising Math500, AIME 2024, AMC, Gaokao, Minerva Math, and Olympiad Bench components.

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) | Math Reasoning Suite (Math500, AIME24, AMC, Gaokao, Minerva Math, Olympiad Bench) |
| Metric | Math500 Score |
| 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

- [Math500 Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-aime24-amc-gaokao-minerva-math-and-olympiad-bench.md?metric=Math500%20Score>): Higher is better; unit: PERCENT.

- [AIME24 Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-aime24-amc-gaokao-minerva-math-and-olympiad-bench.md?metric=AIME24%20Score>): Higher is better; unit: PERCENT.

- [AMC Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-aime24-amc-gaokao-minerva-math-and-olympiad-bench.md?metric=AMC%20Score>): Higher is better; unit: PERCENT.

- [Gaokao Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-aime24-amc-gaokao-minerva-math-and-olympiad-bench.md?metric=Gaokao%20Score>): Higher is better; unit: PERCENT.

- [Minerva Math Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-aime24-amc-gaokao-minerva-math-and-olympiad-bench.md?metric=Minerva%20Math%20Score>): Higher is better; unit: PERCENT.

- [Olympiad Bench Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-aime24-amc-gaokao-minerva-math-and-olympiad-bench.md?metric=Olympiad%20Bench%20Score>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-aime24-amc-gaokao-minerva-math-and-olympiad-bench.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Math500 Score | Result date | Report paper |
| --- | --- | --- | --- |
| GRESO | 93.2 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| HIVE | 93 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| DS | 87.9 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| HIVE | 87.2 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| GRESO | 85.5 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| DS | 82.9 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| HIVE | 77.9 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| DS | 77.3 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| GRESO | 77.3 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| HIVE | 53.8 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| DS | 52.4 | Not recorded | 69c60eff0636e5bf4afc84e3 |
| GRESO | 51.8 | Not recorded | 69c60eff0636e5bf4afc84e3 |

### GRESO

Math500 Score: 93.2. Result ID: 69c67e6947f34ce924b0731e.

[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","#Rollout":"6.3M (2.1×)"}. This record does not assert independent reproduction.

### HIVE

Math500 Score: 93. Result ID: 69c67e6947f34ce924b0731f.

[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","#Rollout":"3.9M (3.4×)"}. This record does not assert independent reproduction.

### DS

Math500 Score: 87.9. Result ID: 69c67e6947f34ce924b07317.

[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":"DeepSeek-R1-Distill-Qwen-1.5B","#Rollout":"2.4M (1.0×)"}. This record does not assert independent reproduction.

### HIVE

Math500 Score: 87.2. Result ID: 69c67e6947f34ce924b07319.

[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":"DeepSeek-R1-Distill-Qwen-1.5B","#Rollout":"1.5M (1.6×)"}. This record does not assert independent reproduction.

### GRESO

Math500 Score: 85.5. Result ID: 69c67e6947f34ce924b07318.

[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":"DeepSeek-R1-Distill-Qwen-1.5B","#Rollout":"1.6M (1.5×)"}. This record does not assert independent reproduction.

### DS

Math500 Score: 82.9. Result ID: 69c67e6947f34ce924b0731d.

[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","#Rollout":"13.1M (1.0×)"}. This record does not assert independent reproduction.

### HIVE

Math500 Score: 77.9. Result ID: 69c67e6947f34ce924b07316.

[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","#Rollout":"3.1M (2.5×)"}. This record does not assert independent reproduction.

### DS

Math500 Score: 77.3. Result ID: 69c67e6947f34ce924b07314.

[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","#Rollout":"7.6M (1.0×)"}. This record does not assert independent reproduction.

### GRESO

Math500 Score: 77.3. Result ID: 69c67e6947f34ce924b07315.

[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","#Rollout":"3.3M (2.3×)"}. This record does not assert independent reproduction.

### HIVE

Math500 Score: 53.8. Result ID: 69c67e6947f34ce924b0731c.

[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":"Llama3.2-3b-Instruct","#Rollout":"4.8M (2.4×)"}. This record does not assert independent reproduction.

### DS

Math500 Score: 52.4. Result ID: 69c67e6947f34ce924b0731a.

[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":"Llama3.2-3b-Instruct","#Rollout":"11.4M (1.0×)"}. This record does not assert independent reproduction.

### GRESO

Math500 Score: 51.8. Result ID: 69c67e6947f34ce924b0731b.

[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":"Llama3.2-3b-Instruct","#Rollout":"5.9M (1.9×)"}. This record does not assert independent reproduction.

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