# Mathematics on AMC 24 (avg@32 accuracy)

Source: [Mathematics on AMC 24 (avg@32 accuracy)](<https://www.sota2.com/research/sota/mathematics-on-amc-24-avg-at-32-accuracy>)

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

Data updated: 2026-05-28T08:54:10.778Z

Evaluation of model performance on the AMC 24 dataset for Mathematics tasks, measured using the average accuracy at k=32.

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 | Mathematics |
| Dataset (including any stated split) | AMC 24 |
| Metric | Accuracy (avg@32) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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 (avg@32)](<https://www.sota2.com/research/sota/mathematics-on-amc-24-avg-at-32-accuracy.md?metric=Accuracy%20(avg%4032)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (avg@32) | Result date | Report paper |
| --- | --- | --- | --- |
| IBTPO | 46 | Not recorded | 6a17cc00dbd7150506f81233 |
| TreeRL | 40.5 | Not recorded | 6a17cc00dbd7150506f81233 |
| TreePO | 40.1 | Not recorded | 6a17cc00dbd7150506f81233 |
| IBRO | 39.5 | Not recorded | 6a17cc00dbd7150506f81233 |
| Vanilla GRPO | 39.4 | Not recorded | 6a17cc00dbd7150506f81233 |
| GRPO w/ Entropy Reg† | 39.4 | Not recorded | 6a17cc00dbd7150506f81233 |
| GRPO w/ Clip-higher | 38.9 | Not recorded | 6a17cc00dbd7150506f81233 |
| Initial Model | 26.8 | Not recorded | 6a17cc00dbd7150506f81233 |
| IBTPO | 23.4 | Not recorded | 6a17cc00dbd7150506f81233 |
| IBRO | 20.8 | Not recorded | 6a17cc00dbd7150506f81233 |
| TreeRL | 20.6 | Not recorded | 6a17cc00dbd7150506f81233 |
| GRPO w/ Clip-higher | 20.5 | Not recorded | 6a17cc00dbd7150506f81233 |
| Vanilla GRPO | 19.7 | Not recorded | 6a17cc00dbd7150506f81233 |
| TreePO | 19.5 | Not recorded | 6a17cc00dbd7150506f81233 |
| GRPO w/ Entropy Reg† | 18.8 | Not recorded | 6a17cc00dbd7150506f81233 |
| Initial Model | 15.1 | Not recorded | 6a17cc00dbd7150506f81233 |

### IBTPO

Accuracy (avg@32): 46. Result ID: 6a180298fbc373592c11dc21.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B-Base"}. This record does not assert independent reproduction.

### TreeRL

Accuracy (avg@32): 40.5. Result ID: 6a180298fbc373592c11dc1f.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa796f1e209131cea7d97e.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B-Base"}. This record does not assert independent reproduction.

### TreePO

Accuracy (avg@32): 40.1. Result ID: 6a180298fbc373592c11dc20.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae51e209131cea85c12.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B-Base"}. This record does not assert independent reproduction.

### IBRO

Accuracy (avg@32): 39.5. Result ID: 6a180298fbc373592c11dc1e.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a351e209131cea81c6d.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B-Base"}. This record does not assert independent reproduction.

### Vanilla GRPO

Accuracy (avg@32): 39.4. Result ID: 6a180298fbc373592c11dc1b.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B-Base"}. This record does not assert independent reproduction.

### GRPO w/ Entropy Reg†

Accuracy (avg@32): 39.4. Result ID: 6a180298fbc373592c11dc1d.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B-Base"}. This record does not assert independent reproduction.

### GRPO w/ Clip-higher

Accuracy (avg@32): 38.9. Result ID: 6a180298fbc373592c11dc1c.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B-Base"}. This record does not assert independent reproduction.

### Initial Model

Accuracy (avg@32): 26.8. Result ID: 6a180298fbc373592c11dc1a.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

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

Recorded evaluation configuration: {"Base Model":"Qwen3-8B-Base"}. This record does not assert independent reproduction.

### IBTPO

Accuracy (avg@32): 23.4. Result ID: 6a180298fbc373592c11dc19.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-1.7B-Base"}. This record does not assert independent reproduction.

### IBRO

Accuracy (avg@32): 20.8. Result ID: 6a180298fbc373592c11dc16.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a351e209131cea81c6d.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-1.7B-Base"}. This record does not assert independent reproduction.

### TreeRL

Accuracy (avg@32): 20.6. Result ID: 6a180298fbc373592c11dc17.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa796f1e209131cea7d97e.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-1.7B-Base"}. This record does not assert independent reproduction.

### GRPO w/ Clip-higher

Accuracy (avg@32): 20.5. Result ID: 6a180298fbc373592c11dc14.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-1.7B-Base"}. This record does not assert independent reproduction.

### Vanilla GRPO

Accuracy (avg@32): 19.7. Result ID: 6a180298fbc373592c11dc13.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

Recorded evaluation configuration: {"Base Model":"Qwen3-1.7B-Base"}. This record does not assert independent reproduction.

### TreePO

Accuracy (avg@32): 19.5. Result ID: 6a180298fbc373592c11dc18.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae51e209131cea85c12.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-1.7B-Base"}. This record does not assert independent reproduction.

### GRPO w/ Entropy Reg†

Accuracy (avg@32): 18.8. Result ID: 6a180298fbc373592c11dc15.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

Recorded evaluation configuration: {"Base Model":"Qwen3-1.7B-Base"}. This record does not assert independent reproduction.

### Initial Model

Accuracy (avg@32): 15.1. Result ID: 6a180298fbc373592c11dc12.

[Reporting paper](<https://www.sota2.com/research/paper/6a17cc00dbd7150506f81233.md>)

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

Recorded evaluation configuration: {"Base Model":"Qwen3-1.7B-Base"}. This record does not assert independent reproduction.

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