# Mathematical Reasoning on AIME 2024 (Mean@32)

Source: [Mathematical Reasoning on AIME 2024 (Mean@32)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-mean-at-32>)

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

Data updated: 2026-05-08T07:49:10.616Z

Evaluation of model performance on the AIME 2024 dataset, reporting the Mean score calculated using k=32 samples.

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 | Mean Score (k=32) |
| Unit | SCALAR |
| 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

- [Mean Score (k=32)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-mean-at-32.md?metric=Mean%20Score%20(k%3D32)>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Mean Score (k=32) | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-4B-Base + Resample w/ LOPE (w/ Training Signal Shaping) | 19.9 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen2.5-Math-7B + Resample w/ LOPE (w/ Training Signal Shaping) | 19.58 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-4B-Base + Resample w/ LOPE (w/o Training Signal Shaping) | 19.01 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen2.5-Math-7B + GRPO | 17.66 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen2.5-Math-7B + Resample w/ Naive Prompt | 17.19 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-4B-Base + GRPO | 16.41 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen2.5-Math-7B + Resample w/ LOPE (w/o Training Signal Shaping) | 15.31 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-4B-Base + Resample w/ Naive Prompt | 14.9 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen2.5-Math-7B | 12.9 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-4B-Base | 9.38 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-1.7B-Base + Resample w/ LOPE (w/ Training Signal Shaping) | 8.8 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-1.7B-Base + Resample w/ Naive Prompt | 8.7 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-1.7B-Base + Resample w/ LOPE (w/o Training Signal Shaping) | 7.97 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-1.7B-Base + GRPO | 6.15 | Not recorded | 69fd6df75497b3b670c89346 |
| Qwen3-1.7B-Base | 5.33 | Not recorded | 69fd6df75497b3b670c89346 |

### Qwen3-4B-Base + Resample w/ LOPE (w/ Training Signal Shaping)

Mean Score (k=32): 19.9. Result ID: 69fd957347f34ce924e05a4e.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","Optimization Method":"GRPO + Resample","Prompt Strategy":"LOPE","Training Signal Shaping":"true"}. This record does not assert independent reproduction.

### Qwen2.5-Math-7B + Resample w/ LOPE (w/ Training Signal Shaping)

Mean Score (k=32): 19.58. Result ID: 69fd957347f34ce924e05a53.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-Math-7B","Optimization Method":"GRPO + Resample","Prompt Strategy":"LOPE","Training Signal Shaping":"true"}. This record does not assert independent reproduction.

### Qwen3-4B-Base + Resample w/ LOPE (w/o Training Signal Shaping)

Mean Score (k=32): 19.01. Result ID: 69fd957347f34ce924e05a4d.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","Optimization Method":"GRPO + Resample","Prompt Strategy":"LOPE","Training Signal Shaping":"false"}. This record does not assert independent reproduction.

### Qwen2.5-Math-7B + GRPO

Mean Score (k=32): 17.66. Result ID: 69fd957347f34ce924e05a50.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

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

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

Recorded evaluation configuration: {"Model":"Qwen2.5-Math-7B","Optimization Method":"GRPO"}. This record does not assert independent reproduction.

### Qwen2.5-Math-7B + Resample w/ Naive Prompt

Mean Score (k=32): 17.19. Result ID: 69fd957347f34ce924e05a51.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-Math-7B","Optimization Method":"GRPO + Resample","Prompt Strategy":"Naive Prompt"}. This record does not assert independent reproduction.

### Qwen3-4B-Base + GRPO

Mean Score (k=32): 16.41. Result ID: 69fd957347f34ce924e05a4b.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

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

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

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","Optimization Method":"GRPO"}. This record does not assert independent reproduction.

### Qwen2.5-Math-7B + Resample w/ LOPE (w/o Training Signal Shaping)

Mean Score (k=32): 15.31. Result ID: 69fd957347f34ce924e05a52.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-Math-7B","Optimization Method":"GRPO + Resample","Prompt Strategy":"LOPE","Training Signal Shaping":"false"}. This record does not assert independent reproduction.

### Qwen3-4B-Base + Resample w/ Naive Prompt

Mean Score (k=32): 14.9. Result ID: 69fd957347f34ce924e05a4c.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen3-4B-Base","Optimization Method":"GRPO + Resample","Prompt Strategy":"Naive Prompt"}. This record does not assert independent reproduction.

### Qwen2.5-Math-7B

Mean Score (k=32): 12.9. Result ID: 69fd957347f34ce924e05a4f.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74d81e209131cea6419f.md>)

[Implementation](<https://github.com/QwenLM/Qwen2-Math>)

Recorded evaluation configuration: {"Model":"Qwen2.5-Math-7B","Optimization Method":"Base"}. This record does not assert independent reproduction.

### Qwen3-4B-Base

Mean Score (k=32): 9.38. Result ID: 69fd957347f34ce924e05a4a.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

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

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

### Qwen3-1.7B-Base + Resample w/ LOPE (w/ Training Signal Shaping)

Mean Score (k=32): 8.8. Result ID: 69fd957347f34ce924e05a49.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen3-1.7B-Base","Optimization Method":"GRPO + Resample","Prompt Strategy":"LOPE","Training Signal Shaping":"true"}. This record does not assert independent reproduction.

### Qwen3-1.7B-Base + Resample w/ Naive Prompt

Mean Score (k=32): 8.7. Result ID: 69fd957347f34ce924e05a47.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen3-1.7B-Base","Optimization Method":"GRPO + Resample","Prompt Strategy":"Naive Prompt"}. This record does not assert independent reproduction.

### Qwen3-1.7B-Base + Resample w/ LOPE (w/o Training Signal Shaping)

Mean Score (k=32): 7.97. Result ID: 69fd957347f34ce924e05a48.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

Recorded evaluation configuration: {"Model":"Qwen3-1.7B-Base","Optimization Method":"GRPO + Resample","Prompt Strategy":"LOPE","Training Signal Shaping":"false"}. This record does not assert independent reproduction.

### Qwen3-1.7B-Base + GRPO

Mean Score (k=32): 6.15. Result ID: 69fd957347f34ce924e05a46.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

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

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

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

### Qwen3-1.7B-Base

Mean Score (k=32): 5.33. Result ID: 69fd957347f34ce924e05a45.

[Reporting paper](<https://www.sota2.com/research/paper/69fd6df75497b3b670c89346.md>)

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

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

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