# Mathematical Reasoning on AMC 2023 (avg@64, pass@64)

Source: [Mathematical Reasoning on AMC 2023 (avg@64, pass@64)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-avg-at-64-pass-at-64>)

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

Data updated: 2026-05-18T06:57:40.331Z

Evaluation of model performance on the AMC 2023 dataset for Mathematical Reasoning, specifically measured using avg@64 and pass@64 metrics.

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) | AMC 2023 |
| Metric | Avg@64 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [Avg@64](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-avg-at-64-pass-at-64.md?metric=Avg%4064>): Higher is better; unit: PERCENT.

- [Pass@64](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-avg-at-64-pass-at-64.md?metric=Pass%4064>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Avg@64 | Result date | Report paper |
| --- | --- | --- | --- |
| ASPO-Math-30B | 94.9 | Not recorded | 68fa7bf11e209131cea8b7bc |
| GRPO | 91.9 | Not recorded | 68fa7bf11e209131cea8b7bc |
| ASPO-Math-8B | 89.1 | Not recorded | 68fa7bf11e209131cea8b7bc |
| ASPO-Math-4B | 87.4 | Not recorded | 68fa7bf11e209131cea8b7bc |
| ASPO-Math-1.5B | 87.2 | Not recorded | 68fa7bf11e209131cea8b7bc |
| Nemotron-1.5B | 86.1 | Not recorded | 68fa7bf11e209131cea8b7bc |
| GRPO | 84.3 | Not recorded | 68fa7bf11e209131cea8b7bc |
| GRPO | 84.1 | Not recorded | 68fa7bf11e209131cea8b7bc |
| DeepScaleR-1.5B | 81.3 | Not recorded | 68fa7bf11e209131cea8b7bc |
| GRPO | 80.3 | Not recorded | 68fa7bf11e209131cea8b7bc |
| Qwen3-30B-A3B | 74.3 | Not recorded | 68fa7bf11e209131cea8b7bc |
| DeepSeek-R1-1.5B | 70.7 | Not recorded | 68fa7bf11e209131cea8b7bc |
| Qwen3-8B | 68.9 | Not recorded | 68fa7bf11e209131cea8b7bc |
| Qwen3-4B | 67.7 | Not recorded | 68fa7bf11e209131cea8b7bc |

### ASPO-Math-30B

Avg@64: 94.9. Result ID: 6a0ab74047f34ce924f04629.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### GRPO

Avg@64: 91.9. Result ID: 6a0ab74047f34ce924f04628.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

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

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

Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### ASPO-Math-8B

Avg@64: 89.1. Result ID: 6a0ab74047f34ce924f04626.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

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

### ASPO-Math-4B

Avg@64: 87.4. Result ID: 6a0ab74047f34ce924f04623.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction.

### ASPO-Math-1.5B

Avg@64: 87.2. Result ID: 6a0ab74047f34ce924f04620.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### Nemotron-1.5B

Avg@64: 86.1. Result ID: 6a0ab74047f34ce924f0461f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79041e209131cea7bb2d.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### GRPO

Avg@64: 84.3. Result ID: 6a0ab74047f34ce924f04622.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

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

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

Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction.

### GRPO

Avg@64: 84.1. Result ID: 6a0ab74047f34ce924f04625.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

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

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

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

### DeepScaleR-1.5B

Avg@64: 81.3. Result ID: 6a0ab74047f34ce924f0461e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### GRPO

Avg@64: 80.3. Result ID: 6a0ab74047f34ce924f0461d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

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

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

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### Qwen3-30B-A3B

Avg@64: 74.3. Result ID: 6a0ab74047f34ce924f04627.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

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

Recorded evaluation configuration: {"Backbone":"Qwen3-30B-A3B"}. This record does not assert independent reproduction.

### DeepSeek-R1-1.5B

Avg@64: 70.7. Result ID: 6a0ab74047f34ce924f0461c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### Qwen3-8B

Avg@64: 68.9. Result ID: 6a0ab74047f34ce924f04624.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

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

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

### Qwen3-4B

Avg@64: 67.7. Result ID: 6a0ab74047f34ce924f04621.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bf11e209131cea8b7bc.md>)

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

Recorded evaluation configuration: {"Backbone":"Qwen3-4B"}. This record does not assert independent reproduction.

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