# Mathematical Reasoning on MATH (test) (Model Performance Scores)

Source: [Mathematical Reasoning on MATH (test) (Model Performance Scores)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-test-model-performance-scores>)

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

Data updated: 2026-03-04T13:10:34.839Z

Evaluation of various LLMs on the test split of the MATH dataset, reporting individual model performance scores and the average across the compared models.

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 (test) |
| Metric | Accuracy (MATH Test) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Accuracy (MATH Test)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-test-model-performance-scores.md?metric=Accuracy%20(MATH%20Test)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (MATH Test) | Result date | Report paper |
| --- | --- | --- | --- |
| Aflow | 80.83 | Not recorded | 69a66c142d603e6de3e3cd9e |
| CARD | 73.33 | Not recorded | 69a66c142d603e6de3e3cd9e |
| G-designer | 70 | Not recorded | 69a66c142d603e6de3e3cd9e |
| GPTswarm | 67.5 | Not recorded | 69a66c142d603e6de3e3cd9e |
| CoT | 61.66 | Not recorded | 69a66c142d603e6de3e3cd9e |
| Random-graph | 60 | Not recorded | 69a66c142d603e6de3e3cd9e |
| LLM-Debate | 59.16 | Not recorded | 69a66c142d603e6de3e3cd9e |
| Vanilla | 59.16 | Not recorded | 69a66c142d603e6de3e3cd9e |

### Aflow

Accuracy (MATH Test): 80.83. Result ID: 69a82f336dbb7075b94e9464.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78111e209131cea769ef.md>)

Recorded evaluation configuration: {"Multi-agent":"Yes","Automated Topology":"Yes","Conditional Configuration":"No"}. This record does not assert independent reproduction.

### CARD

Accuracy (MATH Test): 73.33. Result ID: 69a82f336dbb7075b94e9466.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

Recorded evaluation configuration: {"Multi-agent":"Yes","Automated Topology":"Yes","Conditional Configuration":"Yes"}. This record does not assert independent reproduction.

### G-designer

Accuracy (MATH Test): 70. Result ID: 69a82f336dbb7075b94e9465.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76e91e209131cea6fe24.md>)

Recorded evaluation configuration: {"Multi-agent":"Yes","Automated Topology":"Yes","Conditional Configuration":"No"}. This record does not assert independent reproduction.

### GPTswarm

Accuracy (MATH Test): 67.5. Result ID: 69a82f336dbb7075b94e9463.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

Recorded evaluation configuration: {"Multi-agent":"Yes","Automated Topology":"Yes","Conditional Configuration":"No"}. This record does not assert independent reproduction.

### CoT

Accuracy (MATH Test): 61.66. Result ID: 69a82f336dbb7075b94e9460.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Multi-agent":"No","Automated Topology":"No","Conditional Configuration":"No"}. This record does not assert independent reproduction.

### Random-graph

Accuracy (MATH Test): 60. Result ID: 69a82f336dbb7075b94e9461.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

Recorded evaluation configuration: {"Multi-agent":"Yes","Automated Topology":"No","Conditional Configuration":"No"}. This record does not assert independent reproduction.

### LLM-Debate

Accuracy (MATH Test): 59.16. Result ID: 69a82f336dbb7075b94e9462.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6a1e209131cea456e2.md>)

Recorded evaluation configuration: {"Multi-agent":"Yes","Automated Topology":"No","Conditional Configuration":"No"}. This record does not assert independent reproduction.

### Vanilla

Accuracy (MATH Test): 59.16. Result ID: 69a82f336dbb7075b94e945f.

[Reporting paper](<https://www.sota2.com/research/paper/69a66c142d603e6de3e3cd9e.md>)

Recorded evaluation configuration: {"Multi-agent":"No","Automated Topology":"No","Conditional Configuration":"No"}. This record does not assert independent reproduction.

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