# Mathematical Reasoning on MATH 500 (Accuracy and Delta Change)

Source: [Mathematical Reasoning on MATH 500 (Accuracy and Delta Change)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-and-delta-change>)

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

Data updated: 2026-04-06T08:44:15.025Z

Evaluation of model performance on mathematical reasoning problems using the MATH 500 dataset, reporting primary Accuracy and relative change (Δ %).

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 500 |
| Metric | 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

- [Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-and-delta-change.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Accuracy Delta (%)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-and-delta-change.md?metric=Accuracy%20Delta%20(%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek-R1-0528 | 98.8 | Not recorded | 69d33ded7d0172140ec735d6 |
| Qwen3-30B-A3B-Thinking | 97.5 | Not recorded | 69d33ded7d0172140ec735d6 |
| Qwen3-8B | 96.4 | Not recorded | 69d33ded7d0172140ec735d6 |
| DeepSeek-V3.1 | 92.2 | Not recorded | 69d33ded7d0172140ec735d6 |
| Qwen3-30B-A3B-Instruct | 88.2 | Not recorded | 69d33ded7d0172140ec735d6 |
| Qwen3-8B | 86.8 | Not recorded | 69d33ded7d0172140ec735d6 |

### DeepSeek-R1-0528

Accuracy: 98.8. Result ID: 69d3725e47f34ce924bb5c57.

[Reporting paper](<https://www.sota2.com/research/paper/69d33ded7d0172140ec735d6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76a91e209131cea6e3eb.md>)

Recorded evaluation configuration: {"Thinking Mode":"Thinking"}. This record does not assert independent reproduction.

### Qwen3-30B-A3B-Thinking

Accuracy: 97.5. Result ID: 69d3725e47f34ce924bb5c53.

[Reporting paper](<https://www.sota2.com/research/paper/69d33ded7d0172140ec735d6.md>)

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

Recorded evaluation configuration: {"Thinking Mode":"Thinking"}. This record does not assert independent reproduction.

### Qwen3-8B

Accuracy: 96.4. Result ID: 69d3725e47f34ce924bb5c55.

[Reporting paper](<https://www.sota2.com/research/paper/69d33ded7d0172140ec735d6.md>)

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

Recorded evaluation configuration: {"Thinking Mode":"Thinking"}. This record does not assert independent reproduction.

### DeepSeek-V3.1

Accuracy: 92.2. Result ID: 69d3725e47f34ce924bb5c56.

[Reporting paper](<https://www.sota2.com/research/paper/69d33ded7d0172140ec735d6.md>)

Recorded evaluation configuration: {"Thinking Mode":"No Thinking"}. This record does not assert independent reproduction.

### Qwen3-30B-A3B-Instruct

Accuracy: 88.2. Result ID: 69d3725e47f34ce924bb5c52.

[Reporting paper](<https://www.sota2.com/research/paper/69d33ded7d0172140ec735d6.md>)

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

Recorded evaluation configuration: {"Thinking Mode":"No Thinking"}. This record does not assert independent reproduction.

### Qwen3-8B

Accuracy: 86.8. Result ID: 69d3725e47f34ce924bb5c54.

[Reporting paper](<https://www.sota2.com/research/paper/69d33ded7d0172140ec735d6.md>)

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

Recorded evaluation configuration: {"Thinking Mode":"No Thinking"}. This record does not assert independent reproduction.

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