# Mathematical Problem Solving on Apex 2025 (Score %)

Source: [Mathematical Problem Solving on Apex 2025 (Score %)](<https://www.sota2.com/research/sota/mathematical-problem-solving-on-apex-2025-score-percent>)

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

Data updated: 2026-05-20T08:03:50.231Z

Evaluation of model performance on the Apex 2025 dataset for mathematical problem solving, measured by Score (%).

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 Problem Solving |
| Dataset (including any stated split) | Apex 2025 |
| Metric | Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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

- [Score](<https://www.sota2.com/research/sota/mathematical-problem-solving-on-apex-2025-score-percent.md?metric=Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| STAR-PólyaMath | 93.75 | Not recorded | 6a0d4002f984739ed6737770 |
| GPT-5.5 | 80.21 | Not recorded | 6a0d4002f984739ed6737770 |
| Gemini 3.1 Pro | 60.94 | Not recorded | 6a0d4002f984739ed6737770 |
| GPT-5.4 | 54.17 | Not recorded | 6a0d4002f984739ed6737770 |
| Claude Opus 4.7 | 40.62 | Not recorded | 6a0d4002f984739ed6737770 |
| Claude Opus 4.6 | 34.45 | Not recorded | 6a0d4002f984739ed6737770 |
| DeepSeek-v4-Pro | 28.12 | Not recorded | 6a0d4002f984739ed6737770 |
| Kimi K2.6 | 23.96 | Not recorded | 6a0d4002f984739ed6737770 |
| Gemini 3 Pro | 23.44 | Not recorded | 6a0d4002f984739ed6737770 |
| GPT-5.2 | 13.54 | Not recorded | 6a0d4002f984739ed6737770 |
| GLM 5.1 | 11.46 | Not recorded | 6a0d4002f984739ed6737770 |
| DeepSeek-v3.2-Speciale | 9.38 | Not recorded | 6a0d4002f984739ed6737770 |
| Kimi K2.5 | 8.85 | Not recorded | 6a0d4002f984739ed6737770 |

### STAR-PólyaMath

Score: 93.75. Result ID: 6a0d6a09fbc373592c0546b5.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Backbone":"all GPT-5.5xh"}. This record does not assert independent reproduction.

### GPT-5.5

Score: 80.21. Result ID: 6a0d6a09fbc373592c0546a9.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Reasoning Effort":"xhigh"}. This record does not assert independent reproduction.

### Gemini 3.1 Pro

Score: 60.94. Result ID: 6a0d6a09fbc373592c0546ac.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-5.4

Score: 54.17. Result ID: 6a0d6a09fbc373592c0546aa.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Reasoning Effort":"xhigh"}. This record does not assert independent reproduction.

### Claude Opus 4.7

Score: 40.62. Result ID: 6a0d6a09fbc373592c0546ae.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Reasoning Effort":"xhigh"}. This record does not assert independent reproduction.

### Claude Opus 4.6

Score: 34.45. Result ID: 6a0d6a09fbc373592c0546af.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Reasoning Effort":"high"}. This record does not assert independent reproduction.

### DeepSeek-v4-Pro

Score: 28.12. Result ID: 6a0d6a09fbc373592c0546b0.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Reasoning Effort":"Max"}. This record does not assert independent reproduction.

### Kimi K2.6

Score: 23.96. Result ID: 6a0d6a09fbc373592c0546b2.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Reasoning Effort":"Think"}. This record does not assert independent reproduction.

### Gemini 3 Pro

Score: 23.44. Result ID: 6a0d6a09fbc373592c0546ad.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### GPT-5.2

Score: 13.54. Result ID: 6a0d6a09fbc373592c0546ab.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Reasoning Effort":"high"}. This record does not assert independent reproduction.

### GLM 5.1

Score: 11.46. Result ID: 6a0d6a09fbc373592c0546b4.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DeepSeek-v3.2-Speciale

Score: 9.38. Result ID: 6a0d6a09fbc373592c0546b1.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Kimi K2.5

Score: 8.85. Result ID: 6a0d6a09fbc373592c0546b3.

[Reporting paper](<https://www.sota2.com/research/paper/6a0d4002f984739ed6737770.md>)

Recorded evaluation configuration: {"Reasoning Effort":"Think"}. This record does not assert independent reproduction.

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