# Mathematical Reasoning on MATH500 (Acc, TF, Acc/TF)

Source: [Mathematical Reasoning on MATH500 (Acc, TF, Acc/TF)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-acc-tf-acc-tf>)

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

Data updated: 2026-02-26T05:26:45.679Z

Evaluation of model performance on the MATH500 dataset for mathematical reasoning, reporting standard Accuracy (Acc), a factor 'TF', and the derived ratio Acc/TF.

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) | MATH500 |
| Metric | Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 30 of 30 |
| 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

- [Acc](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-acc-tf-acc-tf.md?metric=Acc>): Higher is better; unit: PERCENT.

- [Reasoning Factor (TF)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-acc-tf-acc-tf.md?metric=Reasoning%20Factor%20(TF)>): Higher is better; unit: SCALAR.

- [Acc/TF Ratio](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-acc-tf-acc-tf.md?metric=Acc%2FTF%20Ratio>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Acc | Result date | Report paper |
| --- | --- | --- | --- |
| ASC | 83.8 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (offline) | 83.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (online) | 83.6 | Not recorded | 695de86953fdd5c361743ab1 |
| SC | 82.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ESC | 82.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (offline) | 81.2 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (online) | 81.2 | Not recorded | 695de86953fdd5c361743ab1 |
| ASC | 80.8 | Not recorded | 695de86953fdd5c361743ab1 |
| SC | 80.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ESC | 80.6 | Not recorded | 695de86953fdd5c361743ab1 |
| pass@1 | 77.6 | Not recorded | 695de86953fdd5c361743ab1 |
| SC | 72.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ESC | 72.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ASC | 72.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (online) | 72.2 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (offline) | 71.8 | Not recorded | 695de86953fdd5c361743ab1 |
| SC | 71.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ESC | 71.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ASC | 71.6 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (offline) | 71.4 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (online) | 71.4 | Not recorded | 695de86953fdd5c361743ab1 |
| pass@1 | 71.2 | Not recorded | 695de86953fdd5c361743ab1 |
| pass@1 | 63.2 | Not recorded | 695de86953fdd5c361743ab1 |
| pass@1 | 61.8 | Not recorded | 695de86953fdd5c361743ab1 |
| ASC | 55 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (offline) | 55 | Not recorded | 695de86953fdd5c361743ab1 |
| SC | 54.8 | Not recorded | 695de86953fdd5c361743ab1 |
| ESC | 54.8 | Not recorded | 695de86953fdd5c361743ab1 |
| ReASC (online) | 53.4 | Not recorded | 695de86953fdd5c361743ab1 |
| pass@1 | 41.4 | Not recorded | 695de86953fdd5c361743ab1 |

### ASC

Acc: 83.8. Result ID: 6996a11d5698665ec4ea9cb2.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713f1e209131cea5017a.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-27B"}. This record does not assert independent reproduction.

### ReASC (offline)

Acc: 83.6. Result ID: 6996a11d5698665ec4ea9cb3.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-27B"}. This record does not assert independent reproduction.

### ReASC (online)

Acc: 83.6. Result ID: 6996a11d5698665ec4ea9cb4.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-27B"}. This record does not assert independent reproduction.

### SC

Acc: 82.6. Result ID: 6996a11d5698665ec4ea9cb0.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-27B","k":16}. This record does not assert independent reproduction.

### ESC

Acc: 82.6. Result ID: 6996a11d5698665ec4ea9cb1.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d81e209131cea53537.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-27B","w":4}. This record does not assert independent reproduction.

### ReASC (offline)

Acc: 81.2. Result ID: 6996a11d5698665ec4ea9cad.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-7B"}. This record does not assert independent reproduction.

### ReASC (online)

Acc: 81.2. Result ID: 6996a11d5698665ec4ea9cae.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-7B"}. This record does not assert independent reproduction.

### ASC

Acc: 80.8. Result ID: 6996a11d5698665ec4ea9cac.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713f1e209131cea5017a.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-7B"}. This record does not assert independent reproduction.

### SC

Acc: 80.6. Result ID: 6996a11d5698665ec4ea9caa.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-7B","k":16}. This record does not assert independent reproduction.

### ESC

Acc: 80.6. Result ID: 6996a11d5698665ec4ea9cab.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d81e209131cea53537.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-7B","w":4}. This record does not assert independent reproduction.

### pass@1

Acc: 77.6. Result ID: 6996a11d5698665ec4ea9caf.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-27B"}. This record does not assert independent reproduction.

### SC

Acc: 72.6. Result ID: 6996a11d5698665ec4ea9c9e.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-3B","k":16}. This record does not assert independent reproduction.

### ESC

Acc: 72.6. Result ID: 6996a11d5698665ec4ea9c9f.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d81e209131cea53537.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-3B","w":4}. This record does not assert independent reproduction.

### ASC

Acc: 72.6. Result ID: 6996a11d5698665ec4ea9ca0.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713f1e209131cea5017a.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-3B"}. This record does not assert independent reproduction.

### ReASC (online)

Acc: 72.2. Result ID: 6996a11d5698665ec4ea9ca2.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-3B"}. This record does not assert independent reproduction.

### ReASC (offline)

Acc: 71.8. Result ID: 6996a11d5698665ec4ea9ca1.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-3B"}. This record does not assert independent reproduction.

### SC

Acc: 71.6. Result ID: 6996a11d5698665ec4ea9ca4.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-4B","k":16}. This record does not assert independent reproduction.

### ESC

Acc: 71.6. Result ID: 6996a11d5698665ec4ea9ca5.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d81e209131cea53537.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-4B","w":4}. This record does not assert independent reproduction.

### ASC

Acc: 71.6. Result ID: 6996a11d5698665ec4ea9ca6.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713f1e209131cea5017a.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-4B"}. This record does not assert independent reproduction.

### ReASC (offline)

Acc: 71.4. Result ID: 6996a11d5698665ec4ea9ca7.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-4B"}. This record does not assert independent reproduction.

### ReASC (online)

Acc: 71.4. Result ID: 6996a11d5698665ec4ea9ca8.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-4B"}. This record does not assert independent reproduction.

### pass@1

Acc: 71.2. Result ID: 6996a11d5698665ec4ea9ca9.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-7B"}. This record does not assert independent reproduction.

### pass@1

Acc: 63.2. Result ID: 6996a11d5698665ec4ea9ca3.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"GEMMA-3-4B"}. This record does not assert independent reproduction.

### pass@1

Acc: 61.8. Result ID: 6996a11d5698665ec4ea9c9d.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"QWEN-2.5-3B"}. This record does not assert independent reproduction.

### ASC

Acc: 55. Result ID: 6996a11d5698665ec4ea9c9a.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa713f1e209131cea5017a.md>)

Recorded evaluation configuration: {"Model":"LLAMA-3.2-3B"}. This record does not assert independent reproduction.

### ReASC (offline)

Acc: 55. Result ID: 6996a11d5698665ec4ea9c9b.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"LLAMA-3.2-3B"}. This record does not assert independent reproduction.

### SC

Acc: 54.8. Result ID: 6996a11d5698665ec4ea9c98.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Model":"LLAMA-3.2-3B","k":16}. This record does not assert independent reproduction.

### ESC

Acc: 54.8. Result ID: 6996a11d5698665ec4ea9c99.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71d81e209131cea53537.md>)

Recorded evaluation configuration: {"Model":"LLAMA-3.2-3B","w":4}. This record does not assert independent reproduction.

### ReASC (online)

Acc: 53.4. Result ID: 6996a11d5698665ec4ea9c9c.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"LLAMA-3.2-3B"}. This record does not assert independent reproduction.

### pass@1

Acc: 41.4. Result ID: 6996a11d5698665ec4ea9c97.

[Reporting paper](<https://www.sota2.com/research/paper/695de86953fdd5c361743ab1.md>)

Recorded evaluation configuration: {"Model":"LLAMA-3.2-3B"}. This record does not assert independent reproduction.

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