# Mathematical Reasoning on AMC 2023 (Latency)

Source: [Mathematical Reasoning on AMC 2023 (Latency)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-latency>)

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

Data updated: 2026-04-02T08:32:59.766Z

Evaluation of model inference speed on the AMC 2023 dataset for Mathematical Reasoning, measured by latency.

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) | AMC 2023 |
| Metric | Latency (s) |
| Unit | TIME |
| Direction | Lower 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

- [Latency (s)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-latency.md?metric=Latency%20(s)>): Lower is better; unit: TIME.

## Recorded results

| Method | Latency (s) | Result date | Report paper |
| --- | --- | --- | --- |
| RoT + TI | 12.7 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 64.05 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 68.05 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 73.8 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 76.71 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 78.58 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 79.68 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 79.73 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 81.16 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 90.53 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 91.1 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 110.95 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 113.79 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 126.8 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 129.82 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT + TI | 129.89 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 131.91 | Not recorded | 68fa7ba81e209131cea89b29 |
| RAG | 137.25 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT | 142.71 | Not recorded | 68fa7ba81e209131cea89b29 |
| RoT | 155.12 | Not recorded | 68fa7ba81e209131cea89b29 |
| BoT | 174.42 | Not recorded | 68fa7ba81e209131cea89b29 |
| BoT | 268.87 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 317.24 | Not recorded | 68fa7ba81e209131cea89b29 |
| BoT | 324.38 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 337.36 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 343.21 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 413.16 | Not recorded | 68fa7ba81e209131cea89b29 |
| CoT-SC | 420.81 | Not recorded | 68fa7ba81e209131cea89b29 |
| BoT | 438.35 | Not recorded | 68fa7ba81e209131cea89b29 |

### RoT + TI

Latency (s): 12.7. Result ID: 69ce284547f34ce924b74633.

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

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

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

### RoT + TI

Latency (s): 64.05. Result ID: 69ce284547f34ce924b74639.

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

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

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

### CoT

Latency (s): 68.05. Result ID: 69ce284547f34ce924b7462e.

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

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

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

### RoT + TI

Latency (s): 73.8. Result ID: 69ce284547f34ce924b7463f.

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

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

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

### CoT

Latency (s): 76.71. Result ID: 69ce284547f34ce924b74634.

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

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

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

### CoT

Latency (s): 78.58. Result ID: 69ce284547f34ce924b7463a.

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

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

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

### RAG

Latency (s): 79.68. Result ID: 69ce284547f34ce924b7462f.

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

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

### RoT

Latency (s): 79.73. Result ID: 69ce284547f34ce924b74632.

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

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

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

### RAG

Latency (s): 81.16. Result ID: 69ce284547f34ce924b74635.

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

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

### RoT

Latency (s): 90.53. Result ID: 69ce284547f34ce924b7463e.

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

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

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

### RAG

Latency (s): 91.1. Result ID: 69ce284547f34ce924b7463b.

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

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

### RoT

Latency (s): 110.95. Result ID: 69ce284547f34ce924b74638.

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

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

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

### RoT + TI

Latency (s): 113.79. Result ID: 69ce284547f34ce924b74645.

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

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

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

### CoT

Latency (s): 126.8. Result ID: 69ce284547f34ce924b74640.

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

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

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

### RoT

Latency (s): 129.82. Result ID: 69ce284547f34ce924b74644.

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

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

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

### RoT + TI

Latency (s): 129.89. Result ID: 69ce284547f34ce924b7464a.

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

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

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

### RAG

Latency (s): 131.91. Result ID: 69ce284547f34ce924b74647.

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

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

### RAG

Latency (s): 137.25. Result ID: 69ce284547f34ce924b74641.

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

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

### CoT

Latency (s): 142.71. Result ID: 69ce284547f34ce924b74646.

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

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

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

### RoT

Latency (s): 155.12. Result ID: 69ce284547f34ce924b74649.

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

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

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

### BoT

Latency (s): 174.42. Result ID: 69ce284547f34ce924b74630.

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

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

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

### BoT

Latency (s): 268.87. Result ID: 69ce284547f34ce924b7463c.

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

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

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

### CoT-SC

Latency (s): 317.24. Result ID: 69ce284547f34ce924b7463d.

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

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

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

### BoT

Latency (s): 324.38. Result ID: 69ce284547f34ce924b74642.

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

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

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

### CoT-SC

Latency (s): 337.36. Result ID: 69ce284547f34ce924b74637.

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

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

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

### CoT-SC

Latency (s): 343.21. Result ID: 69ce284547f34ce924b74631.

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

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

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

### CoT-SC

Latency (s): 413.16. Result ID: 69ce284547f34ce924b74643.

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

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

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

### CoT-SC

Latency (s): 420.81. Result ID: 69ce284547f34ce924b74648.

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

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

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

### BoT

Latency (s): 438.35. Result ID: 69ce284547f34ce924b74636.

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

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

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

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