# Mathematical Reasoning on AIME 2025 (Accuracy, AVG)

Source: [Mathematical Reasoning on AIME 2025 (Accuracy, AVG)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-accuracy-avg>)

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

Data updated: 2026-02-26T05:31:00.837Z

Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2025 dataset, reporting Accuracy and AVG scores.

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 2025 |
| Metric | Accuracy |
| 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](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-accuracy-avg.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-accuracy-avg.md?metric=Average%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Base | 81.5 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1+235B+QWQ) | 80 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1+235B+QWQ) | 76.67 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1+235B) | 76.67 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1+235B) | 73.33 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1) | 73.33 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1) | 73.13 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| Base | 72.08 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| Base | 70 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1+235B+QWQ) | 69.17 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1) | 67.5 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| Base | 67.08 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1+235B) | 66.67 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1+235B+QWQ) | 65.83 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1+235B) | 64.17 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1) | 55.83 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |

### Base

Accuracy: 81.5. Result ID: 699682ad5698665ec4cac5e2.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"Qwen3-235B-A22B"}. This record does not assert independent reproduction.

### T3S(R1+235B+QWQ)

Accuracy: 80. Result ID: 699682ad5698665ec4cac5e0.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### T3S(R1+235B+QWQ)

Accuracy: 76.67. Result ID: 699682ad5698665ec4cac5d9.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

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

### T3S(R1+235B)

Accuracy: 76.67. Result ID: 699682ad5698665ec4cac5df.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### T3S(R1+235B)

Accuracy: 73.33. Result ID: 699682ad5698665ec4cac5d8.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

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

### T3S(R1)

Accuracy: 73.33. Result ID: 699682ad5698665ec4cac5de.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### T3S(R1)

Accuracy: 73.13. Result ID: 699682ad5698665ec4cac5d7.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

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

### Base

Accuracy: 72.08. Result ID: 699682ad5698665ec4cac5da.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### Base

Accuracy: 70. Result ID: 699682ad5698665ec4cac5e1.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"DeepSeek-R1"}. This record does not assert independent reproduction.

### SFT(R1+235B+QWQ)

Accuracy: 69.17. Result ID: 699682ad5698665ec4cac5dd.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### SFT(R1)

Accuracy: 67.5. Result ID: 699682ad5698665ec4cac5db.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### Base

Accuracy: 67.08. Result ID: 699682ad5698665ec4cac5d3.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

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

### SFT(R1+235B)

Accuracy: 66.67. Result ID: 699682ad5698665ec4cac5dc.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

Recorded evaluation configuration: {"Model":"Qwen3-32B"}. This record does not assert independent reproduction.

### SFT(R1+235B+QWQ)

Accuracy: 65.83. Result ID: 699682ad5698665ec4cac5d6.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

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

### SFT(R1+235B)

Accuracy: 64.17. Result ID: 699682ad5698665ec4cac5d5.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

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

### SFT(R1)

Accuracy: 55.83. Result ID: 699682ad5698665ec4cac5d4.

[Reporting paper](<https://www.sota2.com/research/paper/6969c5f0e25ad2fa9d1ec810.md>)

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

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