# Mathematical Reasoning on MATH 500 (Accuracy and Tokens)

Source: [Mathematical Reasoning on MATH 500 (Accuracy and Tokens)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-and-tokens>)

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

Data updated: 2026-02-26T05:31:11.726Z

Evaluation of model performance on the MATH 500 dataset for mathematical reasoning, reporting standard accuracy and output token count.

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) | MATH 500 |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-and-tokens.md?metric=Accuracy>): Higher is better; unit: SCALAR.

- [Output Tokens](<https://www.sota2.com/research/sota/mathematical-reasoning-on-math-500-accuracy-and-tokens.md?metric=Output%20Tokens>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CARD | 0.868 | Not recorded | 69608b6e53fdd5c36174427b |
| CARD | 0.853 | Not recorded | 69608b6e53fdd5c36174427b |
| RDoLT (3-tier) | 0.852 | Not recorded | 69608b6e53fdd5c36174427b |
| ToT (beam-3) | 0.849 | Not recorded | 69608b6e53fdd5c36174427b |
| Zero-Shot | 0.8457 | Not recorded | 69608b6e53fdd5c36174427b |
| RDoLT (3-tier) | 0.843 | Not recorded | 69608b6e53fdd5c36174427b |
| Zero-Shot | 0.839 | Not recorded | 69608b6e53fdd5c36174427b |
| ToT (beam-3) | 0.832 | Not recorded | 69608b6e53fdd5c36174427b |
| CoT | 0.831 | Not recorded | 69608b6e53fdd5c36174427b |
| CoT | 0.818 | Not recorded | 69608b6e53fdd5c36174427b |
| CARD | 0.751 | Not recorded | 69608b6e53fdd5c36174427b |
| RDoLT (3-tier) | 0.736 | Not recorded | 69608b6e53fdd5c36174427b |
| Zero-Shot | 0.73 | Not recorded | 69608b6e53fdd5c36174427b |
| ToT (beam-3) | 0.728 | Not recorded | 69608b6e53fdd5c36174427b |
| CoT | 0.712 | Not recorded | 69608b6e53fdd5c36174427b |

### CARD

Accuracy: 0.868. Result ID: 6996c5725698665ec410e8e4.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

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

### CARD

Accuracy: 0.853. Result ID: 6996c5725698665ec410e8e3.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

Recorded evaluation configuration: {"Backbone":"DS-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### RDoLT (3-tier)

Accuracy: 0.852. Result ID: 6996c5725698665ec410e8e1.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

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

### ToT (beam-3)

Accuracy: 0.849. Result ID: 6996c5725698665ec410e8de.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea50930.md>)

[Implementation](<https://github.com/princeton-nlp/tree-of-thought-llm>)

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

### Zero-Shot

Accuracy: 0.8457. Result ID: 6996c5725698665ec410e8d8.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

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

### RDoLT (3-tier)

Accuracy: 0.843. Result ID: 6996c5725698665ec410e8e0.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

Recorded evaluation configuration: {"Backbone":"DS-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### Zero-Shot

Accuracy: 0.839. Result ID: 6996c5725698665ec410e8d7.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

Recorded evaluation configuration: {"Backbone":"DS-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### ToT (beam-3)

Accuracy: 0.832. Result ID: 6996c5725698665ec410e8dd.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea50930.md>)

[Implementation](<https://github.com/princeton-nlp/tree-of-thought-llm>)

Recorded evaluation configuration: {"Backbone":"DS-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### CoT

Accuracy: 0.831. Result ID: 6996c5725698665ec410e8db.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.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.

### CoT

Accuracy: 0.818. Result ID: 6996c5725698665ec410e8da.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

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

Recorded evaluation configuration: {"Backbone":"DS-R1-Distill-Qwen-1.5B"}. This record does not assert independent reproduction.

### CARD

Accuracy: 0.751. Result ID: 6996c5725698665ec410e8e2.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

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

### RDoLT (3-tier)

Accuracy: 0.736. Result ID: 6996c5725698665ec410e8df.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

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

### Zero-Shot

Accuracy: 0.73. Result ID: 6996c5725698665ec410e8d6.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

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

### ToT (beam-3)

Accuracy: 0.728. Result ID: 6996c5725698665ec410e8dc.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71551e209131cea50930.md>)

[Implementation](<https://github.com/princeton-nlp/tree-of-thought-llm>)

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

### CoT

Accuracy: 0.712. Result ID: 6996c5725698665ec410e8d9.

[Reporting paper](<https://www.sota2.com/research/paper/69608b6e53fdd5c36174427b.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.

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