# Mathematical Reasoning on OlympiadBench (Accuracy, Think ↓, Route%)

Source: [Mathematical Reasoning on OlympiadBench (Accuracy, Think ↓, Route%)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-accuracy-think-route-percent>)

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

Data updated: 2026-06-23T12:18:51.702Z

Evaluation of model performance on mathematical reasoning problems using the OlympiadBench dataset, measured by Accuracy, Think ↓ rate, and Route%.

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) | OlympiadBench |
| 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-olympiadbench-accuracy-think-route-percent.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Think Rate (↓)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-accuracy-think-route-percent.md?metric=Think%20Rate%20(%E2%86%93)>): Lower is better; unit: PERCENT.

- [Route %](<https://www.sota2.com/research/sota/mathematical-reasoning-on-olympiadbench-accuracy-think-route-percent.md?metric=Route%20%25>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| AT | 71.5 | Not recorded | 6a3a13b9206542251d7c78ca |
| SC-Route | 70.4 | Not recorded | 6a3a13b9206542251d7c78ca |
| DART | 69.8 | Not recorded | 6a3a13b9206542251d7c78ca |
| DART | 69.1 | Not recorded | 6a3a13b9206542251d7c78ca |
| SC-Route | 67.1 | Not recorded | 6a3a13b9206542251d7c78ca |
| AT | 66.1 | Not recorded | 6a3a13b9206542251d7c78ca |
| NT | 63.6 | Not recorded | 6a3a13b9206542251d7c78ca |
| SC-Route | 62 | Not recorded | 6a3a13b9206542251d7c78ca |
| DART | 62 | Not recorded | 6a3a13b9206542251d7c78ca |
| SC-Route | 58.5 | Not recorded | 6a3a13b9206542251d7c78ca |
| DART | 58.5 | Not recorded | 6a3a13b9206542251d7c78ca |
| AT | 54 | Not recorded | 6a3a13b9206542251d7c78ca |
| AT | 53 | Not recorded | 6a3a13b9206542251d7c78ca |
| NT | 51.5 | Not recorded | 6a3a13b9206542251d7c78ca |
| NT | 50.5 | Not recorded | 6a3a13b9206542251d7c78ca |
| NT | 49.8 | Not recorded | 6a3a13b9206542251d7c78ca |

### AT

Accuracy: 71.5. Result ID: 6a3a7992fbc373592c38b4d4.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

### SC-Route

Accuracy: 70.4. Result ID: 6a3a7992fbc373592c38b4d5.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.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.

### DART

Accuracy: 69.8. Result ID: 6a3a7992fbc373592c38b4d6.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

### DART

Accuracy: 69.1. Result ID: 6a3a7992fbc373592c38b4e2.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Hosted API":"true"}. This record does not assert independent reproduction.

### SC-Route

Accuracy: 67.1. Result ID: 6a3a7992fbc373592c38b4e1.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Hosted API":"true"}. This record does not assert independent reproduction.

### AT

Accuracy: 66.1. Result ID: 6a3a7992fbc373592c38b4e0.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Hosted API":"true"}. This record does not assert independent reproduction.

### NT

Accuracy: 63.6. Result ID: 6a3a7992fbc373592c38b4df.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

Recorded evaluation configuration: {"Backbone":"DeepSeek-V3.2","Hosted API":"true"}. This record does not assert independent reproduction.

### SC-Route

Accuracy: 62. Result ID: 6a3a7992fbc373592c38b4d9.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.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.

### DART

Accuracy: 62. Result ID: 6a3a7992fbc373592c38b4da.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

### SC-Route

Accuracy: 58.5. Result ID: 6a3a7992fbc373592c38b4dd.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

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

### DART

Accuracy: 58.5. Result ID: 6a3a7992fbc373592c38b4de.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

### AT

Accuracy: 54. Result ID: 6a3a7992fbc373592c38b4dc.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

### AT

Accuracy: 53. Result ID: 6a3a7992fbc373592c38b4d8.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

### NT

Accuracy: 51.5. Result ID: 6a3a7992fbc373592c38b4d7.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

### NT

Accuracy: 50.5. Result ID: 6a3a7992fbc373592c38b4db.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

### NT

Accuracy: 49.8. Result ID: 6a3a7992fbc373592c38b4d3.

[Reporting paper](<https://www.sota2.com/research/paper/6a3a13b9206542251d7c78ca.md>)

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

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