# Mathematical Reasoning on AIME 2024 (Average@12 accuracy)

Source: [Mathematical Reasoning on AIME 2024 (Average@12 accuracy)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-average-at-12-accuracy>)

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

Data updated: 2026-05-13T08:24:59.863Z

Evaluation of model performance on the AIME 2024 dataset, focusing specifically on the Average@12 accuracy metric.

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) | AIME 2024 |
| Metric | Average@12 Accuracy (AIME 2024) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Average@12 Accuracy (AIME 2024)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-average-at-12-accuracy.md?metric=Average%4012%20Accuracy%20(AIME%202024)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average@12 Accuracy (AIME 2024) | Result date | Report paper |
| --- | --- | --- | --- |
| ATESD | 80.56 | Not recorded | 6a0405badbc836b87d8276de |
| ATESD | 78.06 | Not recorded | 6a0405badbc836b87d8276de |
| OPSD | 77.8 | Not recorded | 6a0405badbc836b87d8276de |
| OPSD | 76.4 | Not recorded | 6a0405badbc836b87d8276de |
| GRPO | 76.4 | Not recorded | 6a0405badbc836b87d8276de |
| Base (Instruct) | 75.8 | Not recorded | 6a0405badbc836b87d8276de |
| GRPO | 75.6 | Not recorded | 6a0405badbc836b87d8276de |
| Base (Instruct) | 74.9 | Not recorded | 6a0405badbc836b87d8276de |
| SFT | 72.3 | Not recorded | 6a0405badbc836b87d8276de |
| SFT | 70.2 | Not recorded | 6a0405badbc836b87d8276de |
| ATESD | 59.17 | Not recorded | 6a0405badbc836b87d8276de |
| OPSD | 57.2 | Not recorded | 6a0405badbc836b87d8276de |
| Base (Instruct) | 51.5 | Not recorded | 6a0405badbc836b87d8276de |
| GRPO | 51.1 | Not recorded | 6a0405badbc836b87d8276de |
| SFT | 48.4 | Not recorded | 6a0405badbc836b87d8276de |

### ATESD

Average@12 Accuracy (AIME 2024): 80.56. Result ID: 6a04354e47f34ce924ea1100.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

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

### ATESD

Average@12 Accuracy (AIME 2024): 78.06. Result ID: 6a04354e47f34ce924ea10fb.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

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

### OPSD

Average@12 Accuracy (AIME 2024): 77.8. Result ID: 6a04354e47f34ce924ea10ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6978471ca2b28e761d87ca01.md>)

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

### OPSD

Average@12 Accuracy (AIME 2024): 76.4. Result ID: 6a04354e47f34ce924ea10fa.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6978471ca2b28e761d87ca01.md>)

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

### GRPO

Average@12 Accuracy (AIME 2024): 76.4. Result ID: 6a04354e47f34ce924ea10fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.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.

### Base (Instruct)

Average@12 Accuracy (AIME 2024): 75.8. Result ID: 6a04354e47f34ce924ea10fc.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.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.

### GRPO

Average@12 Accuracy (AIME 2024): 75.6. Result ID: 6a04354e47f34ce924ea10f9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.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.

### Base (Instruct)

Average@12 Accuracy (AIME 2024): 74.9. Result ID: 6a04354e47f34ce924ea10f7.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.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.

### SFT

Average@12 Accuracy (AIME 2024): 72.3. Result ID: 6a04354e47f34ce924ea10fd.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

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

### SFT

Average@12 Accuracy (AIME 2024): 70.2. Result ID: 6a04354e47f34ce924ea10f8.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

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

### ATESD

Average@12 Accuracy (AIME 2024): 59.17. Result ID: 6a04354e47f34ce924ea10f6.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

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

### OPSD

Average@12 Accuracy (AIME 2024): 57.2. Result ID: 6a04354e47f34ce924ea10f5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6978471ca2b28e761d87ca01.md>)

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

### Base (Instruct)

Average@12 Accuracy (AIME 2024): 51.5. Result ID: 6a04354e47f34ce924ea10f2.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

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

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

### GRPO

Average@12 Accuracy (AIME 2024): 51.1. Result ID: 6a04354e47f34ce924ea10f4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

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

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

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

### SFT

Average@12 Accuracy (AIME 2024): 48.4. Result ID: 6a04354e47f34ce924ea10f3.

[Reporting paper](<https://www.sota2.com/research/paper/6a0405badbc836b87d8276de.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

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

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