# Mathematical Reasoning on AMC 2023 (Accuracy and Token Efficiency)

Source: [Mathematical Reasoning on AMC 2023 (Accuracy and Token Efficiency)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-accuracy-and-token-efficiency>)

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

Data updated: 2026-02-26T05:31:14.521Z

Evaluation of model performance on the AMC 2023 dataset for Mathematical Reasoning, focusing on standard accuracy, average accuracy, and token usage metrics (Tpi, Tok).

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 | 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-amc-2023-accuracy-and-token-efficiency.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Tpi](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-accuracy-and-token-efficiency.md?metric=Tpi>): Lower is better; unit: SCALAR.

- [Total Tokens](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-accuracy-and-token-efficiency.md?metric=Total%20Tokens>): Lower is better; unit: SCALAR.

- [Average Accuracy](<https://www.sota2.com/research/sota/mathematical-reasoning-on-amc-2023-accuracy-and-token-efficiency.md?metric=Average%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-32B-SCALE | 98.44 | Not recorded | 692e72a3d6b0dd334293237a |
| Qwen3-32B-InftyThink | 98.12 | Not recorded | 692e72a3d6b0dd334293237a |
| Qwen3-32B-Majority-Voting | 97.5 | Not recorded | 692e72a3d6b0dd334293237a |
| QwQ-Majority-Voting | 97.5 | Not recorded | 692e72a3d6b0dd334293237a |
| QwQ-InftyThink | 97.19 | Not recorded | 692e72a3d6b0dd334293237a |
| Qwen3-32B-CoT | 96.88 | Not recorded | 692e72a3d6b0dd334293237a |
| QwQ-CoT | 96.88 | Not recorded | 692e72a3d6b0dd334293237a |
| Distill-Llama-70B-SCALE | 96.88 | Not recorded | 692e72a3d6b0dd334293237a |
| QwQ-SCALE | 96.25 | Not recorded | 692e72a3d6b0dd334293237a |
| Distill-Qwen-32B-SCALE | 95.63 | Not recorded | 692e72a3d6b0dd334293237a |
| Distill-Llama-70B-CoT | 95.31 | Not recorded | 692e72a3d6b0dd334293237a |
| Distill-Llama-70B-Majority-Voting | 95 | Not recorded | 692e72a3d6b0dd334293237a |
| Distill-Qwen-32B-CoT | 95 | Not recorded | 692e72a3d6b0dd334293237a |
| Distill-Qwen-32B-Majority-Voting | 95 | Not recorded | 692e72a3d6b0dd334293237a |
| Distill-Llama-70B-InftyThink | 93.75 | Not recorded | 692e72a3d6b0dd334293237a |
| Distill-Qwen-32B-InftyThink | 92.81 | Not recorded | 692e72a3d6b0dd334293237a |

### Qwen3-32B-SCALE

Accuracy: 98.44. Result ID: 6996d4b55698665ec4210e77.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Implementation](<https://github.com/XiaoYang66/DualThinking>)

Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Strategy":"SCALE"}. This record does not assert independent reproduction.

### Qwen3-32B-InftyThink

Accuracy: 98.12. Result ID: 6996d4b55698665ec4210e75.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89728.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Strategy":"InftyThink"}. This record does not assert independent reproduction.

### Qwen3-32B-Majority-Voting

Accuracy: 97.5. Result ID: 6996d4b55698665ec4210e76.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

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

Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Strategy":"Majority-Voting"}. This record does not assert independent reproduction.

### QwQ-Majority-Voting

Accuracy: 97.5. Result ID: 6996d4b55698665ec4210e7a.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

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

Recorded evaluation configuration: {"Backbone":"QwQ","Strategy":"Majority-Voting"}. This record does not assert independent reproduction.

### QwQ-InftyThink

Accuracy: 97.19. Result ID: 6996d4b55698665ec4210e79.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89728.md>)

Recorded evaluation configuration: {"Backbone":"QwQ","Strategy":"InftyThink"}. This record does not assert independent reproduction.

### Qwen3-32B-CoT

Accuracy: 96.88. Result ID: 6996d4b55698665ec4210e74.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

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

Recorded evaluation configuration: {"Backbone":"Qwen3-32B","Strategy":"Chain-of-Thought"}. This record does not assert independent reproduction.

### QwQ-CoT

Accuracy: 96.88. Result ID: 6996d4b55698665ec4210e78.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

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

Recorded evaluation configuration: {"Backbone":"QwQ","Strategy":"Chain-of-Thought"}. This record does not assert independent reproduction.

### Distill-Llama-70B-SCALE

Accuracy: 96.88. Result ID: 6996d4b55698665ec4210e7f.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Implementation](<https://github.com/XiaoYang66/DualThinking>)

Recorded evaluation configuration: {"Backbone":"Distill-Llama-70B","Strategy":"SCALE"}. This record does not assert independent reproduction.

### QwQ-SCALE

Accuracy: 96.25. Result ID: 6996d4b55698665ec4210e7b.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Implementation](<https://github.com/XiaoYang66/DualThinking>)

Recorded evaluation configuration: {"Backbone":"QwQ","Strategy":"SCALE"}. This record does not assert independent reproduction.

### Distill-Qwen-32B-SCALE

Accuracy: 95.63. Result ID: 6996d4b55698665ec4210e83.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Implementation](<https://github.com/XiaoYang66/DualThinking>)

Recorded evaluation configuration: {"Backbone":"Distill-Qwen-32B","Strategy":"SCALE"}. This record does not assert independent reproduction.

### Distill-Llama-70B-CoT

Accuracy: 95.31. Result ID: 6996d4b55698665ec4210e7c.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

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

Recorded evaluation configuration: {"Backbone":"Distill-Llama-70B","Strategy":"Chain-of-Thought"}. This record does not assert independent reproduction.

### Distill-Llama-70B-Majority-Voting

Accuracy: 95. Result ID: 6996d4b55698665ec4210e7e.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

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

Recorded evaluation configuration: {"Backbone":"Distill-Llama-70B","Strategy":"Majority-Voting"}. This record does not assert independent reproduction.

### Distill-Qwen-32B-CoT

Accuracy: 95. Result ID: 6996d4b55698665ec4210e80.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

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

Recorded evaluation configuration: {"Backbone":"Distill-Qwen-32B","Strategy":"Chain-of-Thought"}. This record does not assert independent reproduction.

### Distill-Qwen-32B-Majority-Voting

Accuracy: 95. Result ID: 6996d4b55698665ec4210e82.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

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

Recorded evaluation configuration: {"Backbone":"Distill-Qwen-32B","Strategy":"Majority-Voting"}. This record does not assert independent reproduction.

### Distill-Llama-70B-InftyThink

Accuracy: 93.75. Result ID: 6996d4b55698665ec4210e7d.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89728.md>)

Recorded evaluation configuration: {"Backbone":"Distill-Llama-70B","Strategy":"InftyThink"}. This record does not assert independent reproduction.

### Distill-Qwen-32B-InftyThink

Accuracy: 92.81. Result ID: 6996d4b55698665ec4210e81.

[Reporting paper](<https://www.sota2.com/research/paper/692e72a3d6b0dd334293237a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89728.md>)

Recorded evaluation configuration: {"Backbone":"Distill-Qwen-32B","Strategy":"InftyThink"}. This record does not assert independent reproduction.

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