# Mathematical Reasoning on MATH500 (Acc., Len., #Relf./Ans.)

Source: [Mathematical Reasoning on MATH500 (Acc., Len., #Relf./Ans.)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-acc-len-sharp-relf-ans>)

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

Data updated: 2026-05-01T07:33:03.952Z

Evaluation of model performance on the MATH500 dataset for mathematical reasoning, reporting accuracy, output length, and the count of references per answer.

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 | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-acc-len-sharp-relf-ans.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Output Length](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-acc-len-sharp-relf-ans.md?metric=Output%20Length>): Higher is better; unit: SCALAR.

- [References per Answer](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math500-acc-len-sharp-relf-ans.md?metric=References%20per%20Answer>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PLE | 94.8 | Not recorded | 69f4336355a3c32af89fcf86 |
| Hybrid | 92.02 | Not recorded | 69f4336355a3c32af89fcf86 |
| SFT-only | 86.5 | Not recorded | 69f4336355a3c32af89fcf86 |
| PLE | 86 | Not recorded | 69f4336355a3c32af89fcf86 |
| PLE | 83.2 | Not recorded | 69f4336355a3c32af89fcf86 |
| Hybrid | 82.22 | Not recorded | 69f4336355a3c32af89fcf86 |
| PLE | 80.8 | Not recorded | 69f4336355a3c32af89fcf86 |
| SFT-only | 63.56 | Not recorded | 69f4336355a3c32af89fcf86 |
| Instruct | 59.94 | Not recorded | 69f4336355a3c32af89fcf86 |

### PLE

Accuracy: 94.8. Result ID: 69f4559747f34ce924d9de0b.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B","Mode":"Think"}. This record does not assert independent reproduction.

### Hybrid

Accuracy: 92.02. Result ID: 69f4559747f34ce924d9de09.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B","Mode":"Think"}. This record does not assert independent reproduction.

### SFT-only

Accuracy: 86.5. Result ID: 69f4559747f34ce924d9de05.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1c1e209131cea8c661.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-7B","Mode":"Think"}. This record does not assert independent reproduction.

### PLE

Accuracy: 86. Result ID: 69f4559747f34ce924d9de07.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-7B","Mode":"Think"}. This record does not assert independent reproduction.

### PLE

Accuracy: 83.2. Result ID: 69f4559747f34ce924d9de08.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-7B","Mode":"No-think"}. This record does not assert independent reproduction.

### Hybrid

Accuracy: 82.22. Result ID: 69f4559747f34ce924d9de0a.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B","Mode":"No-think"}. This record does not assert independent reproduction.

### PLE

Accuracy: 80.8. Result ID: 69f4559747f34ce924d9de0c.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B","Mode":"No-think"}. This record does not assert independent reproduction.

### SFT-only

Accuracy: 63.56. Result ID: 69f4559747f34ce924d9de06.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1c1e209131cea8c661.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-7B","Mode":"No-think"}. This record does not assert independent reproduction.

### Instruct

Accuracy: 59.94. Result ID: 69f4559747f34ce924d9de04.

[Reporting paper](<https://www.sota2.com/research/paper/69f4336355a3c32af89fcf86.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-7B","Mode":"No-think"}. This record does not assert independent reproduction.

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