# Mathematical Reasoning on AIME 2024 (Accuracy and AVG)

Source: [Mathematical Reasoning on AIME 2024 (Accuracy and AVG)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-accuracy-and-avg>)

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

Data updated: 2026-02-26T05:31:00.820Z

Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2024 dataset, reporting Accuracy and the AVG 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 | 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-2024-accuracy-and-avg.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [AVG](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2024-accuracy-and-avg.md?metric=AVG>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| T3S(R1+235B+QWQ) | 86.67 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| Base | 85.7 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1+235B+QWQ) | 84.17 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1+235B) | 84.17 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1+235B) | 83.33 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1) | 83.33 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1+235B) | 81.67 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| Base | 81.46 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| T3S(R1) | 80 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| Base | 79.8 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1+235B+QWQ) | 78.33 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1) | 76.67 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| Base | 75.83 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1+235B) | 75 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1+235B+QWQ) | 73.33 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |
| SFT(R1) | 72.5 | Not recorded | 6969c5f0e25ad2fa9d1ec810 |

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

Accuracy: 86.67. Result ID: 699682ad5698665ec4cac5d0.

[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.

### Base

Accuracy: 85.7. Result ID: 699682ad5698665ec4cac5d2.

[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: 84.17. Result ID: 699682ad5698665ec4cac5c9.

[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: 84.17. Result ID: 699682ad5698665ec4cac5cf.

[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: 83.33. Result ID: 699682ad5698665ec4cac5c8.

[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: 83.33. Result ID: 699682ad5698665ec4cac5ce.

[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.

### SFT(R1+235B)

Accuracy: 81.67. Result ID: 699682ad5698665ec4cac5cc.

[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: 81.46. Result ID: 699682ad5698665ec4cac5ca.

[Reporting 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: 80. Result ID: 699682ad5698665ec4cac5c7.

[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: 79.8. Result ID: 699682ad5698665ec4cac5d1.

[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: 78.33. Result ID: 699682ad5698665ec4cac5cd.

[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: 76.67. Result ID: 699682ad5698665ec4cac5cb.

[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: 75.83. Result ID: 699682ad5698665ec4cac5c3.

[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: 75. Result ID: 699682ad5698665ec4cac5c5.

[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+QWQ)

Accuracy: 73.33. Result ID: 699682ad5698665ec4cac5c6.

[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: 72.5. Result ID: 699682ad5698665ec4cac5c4.

[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.
