# Mathematical Reasoning on AIME 2025 (Acc %, Tokens)

Source: [Mathematical Reasoning on AIME 2025 (Acc %, Tokens)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-acc-percent-tokens>)

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

Data updated: 2026-04-02T08:32:59.837Z

Evaluation of model performance on the American Invitational Mathematics Examination (AIME) 2025 dataset, reporting general accuracy percentage and total tokens generated or used.

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 | 29 of 29 |
| 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-acc-percent-tokens.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Total Tokens](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-2025-acc-percent-tokens.md?metric=Total%20Tokens>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| RAG | 86.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 80 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 80 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 80 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 73.33 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 66.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 66.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 66.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 66.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 60 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 60 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 60 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 60 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 53.33 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 53.33 | Not recorded | 68fa7ba81e209131cea89b29 |
| BoT | 33.33 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 26.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 26.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| BoT | 26.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 20 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 20 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 20 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 13.33 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 13.33 | Not recorded | 68fa7ba81e209131cea89b29 |
| BoT | 13.33 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 6.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| BoT | 6.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 6.67 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 6.67 | Not recorded | 68fa7ba81e209131cea89b29 |

### RAG

Accuracy: 86.67. Result ID: 69ce284547f34ce924b74670.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### CoT-SC

Accuracy: 80. Result ID: 69ce284547f34ce924b74666.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

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

### CoT-SC

Accuracy: 80. Result ID: 69ce284547f34ce924b7466c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

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

### RoT

Accuracy: 80. Result ID: 69ce284547f34ce924b74672.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### CoT

Accuracy: 73.33. Result ID: 69ce284547f34ce924b7466f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### RoT + TI

Accuracy: 66.67. Result ID: 69ce284547f34ce924b74668.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### RAG

Accuracy: 66.67. Result ID: 69ce284547f34ce924b7466a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### CoT-SC

Accuracy: 66.67. Result ID: 69ce284547f34ce924b74671.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### RoT + TI

Accuracy: 66.67. Result ID: 69ce284547f34ce924b74673.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-14B"}. This record does not assert independent reproduction.

### RAG

Accuracy: 60. Result ID: 69ce284547f34ce924b74664.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### RoT

Accuracy: 60. Result ID: 69ce284547f34ce924b74667.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### CoT

Accuracy: 60. Result ID: 69ce284547f34ce924b74669.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

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

### RoT

Accuracy: 60. Result ID: 69ce284547f34ce924b7466d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### CoT

Accuracy: 53.33. Result ID: 69ce284547f34ce924b74663.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

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

### RoT + TI

Accuracy: 53.33. Result ID: 69ce284547f34ce924b7466e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### BoT

Accuracy: 33.33. Result ID: 69ce284547f34ce924b7466b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75381e209131cea66864.md>)

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

### CoT

Accuracy: 26.67. Result ID: 69ce284547f34ce924b7465d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

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

### RAG

Accuracy: 26.67. Result ID: 69ce284547f34ce924b7465e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### BoT

Accuracy: 26.67. Result ID: 69ce284547f34ce924b74665.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75381e209131cea66864.md>)

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

### CoT-SC

Accuracy: 20. Result ID: 69ce284547f34ce924b74660.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

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

### RoT

Accuracy: 20. Result ID: 69ce284547f34ce924b74661.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### RoT + TI

Accuracy: 20. Result ID: 69ce284547f34ce924b74662.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

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

### RAG

Accuracy: 13.33. Result ID: 69ce284547f34ce924b74658.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-0.6B"}. This record does not assert independent reproduction.

### CoT-SC

Accuracy: 13.33. Result ID: 69ce284547f34ce924b7465a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb61e209131cea41b33.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-0.6B"}. This record does not assert independent reproduction.

### BoT

Accuracy: 13.33. Result ID: 69ce284547f34ce924b7465f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75381e209131cea66864.md>)

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

### CoT

Accuracy: 6.67. Result ID: 69ce284547f34ce924b74657.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-0.6B"}. This record does not assert independent reproduction.

### BoT

Accuracy: 6.67. Result ID: 69ce284547f34ce924b74659.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75381e209131cea66864.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-0.6B"}. This record does not assert independent reproduction.

### RoT

Accuracy: 6.67. Result ID: 69ce284547f34ce924b7465b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-0.6B"}. This record does not assert independent reproduction.

### RoT + TI

Accuracy: 6.67. Result ID: 69ce284547f34ce924b7465c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba81e209131cea89b29.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-0.6B"}. This record does not assert independent reproduction.

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