# Mathematical Reasoning on HMMT25 (Pass@1, Pass@128)

Source: [Mathematical Reasoning on HMMT25 (Pass@1, Pass@128)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-pass-at-1-pass-at-128>)

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

Data updated: 2026-06-01T09:15:23.517Z

Evaluation of model performance on the HMMT25 dataset for mathematical reasoning, specifically reporting Pass@1 and Pass@128 metrics.

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) | HMMT25 |
| Metric | Pass@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 30 of 30 |
| 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

- [Pass@1](<https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-pass-at-1-pass-at-128.md?metric=Pass%401>): Higher is better; unit: PERCENT.

- [Pass@128](<https://www.sota2.com/research/sota/mathematical-reasoning-on-hmmt25-pass-at-1-pass-at-128.md?metric=Pass%40128>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 | Result date | Report paper |
| --- | --- | --- | --- |
| SRGen | 28 | Not recorded | 68fa7bd01e209131cea8aa62 |
| OXAFull | 26.6 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| OXAMLE | 26.5 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| Self-Refine | 25.3 | Not recorded | 68fa7bd01e209131cea8aa62 |
| OXAMLE | 24.5 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SFT | 24.4 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SFT | 23.6 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| CoT | 23.3 | Not recorded | 68fa7bd01e209131cea8aa62 |
| OXAFull | 23.1 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SFTLP | 21.3 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| OXAMLE | 19.7 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SFTLP | 19.3 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SRGen | 19.3 | Not recorded | 68fa7bd01e209131cea8aa62 |
| OXAFull | 19.1 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| OXAMLE | 18.5 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| OXAFull | 18.2 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SRGen | 18 | Not recorded | 68fa7bd01e209131cea8aa62 |
| Self-Refine | 16 | Not recorded | 68fa7bd01e209131cea8aa62 |
| CoT | 15.3 | Not recorded | 68fa7bd01e209131cea8aa62 |
| Self-Refine | 14.7 | Not recorded | 68fa7bd01e209131cea8aa62 |
| CoT | 14 | Not recorded | 68fa7bd01e209131cea8aa62 |
| SFT | 13.8 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SFT | 11.6 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SFTLP | 9.5 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SFTLP | 7.1 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| SRGen | 3.3 | Not recorded | 68fa7bd01e209131cea8aa62 |
| CoT | 1.3 | Not recorded | 68fa7bd01e209131cea8aa62 |
| Base | 0.6 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| Base | 0.5 | Not recorded | 69ba31ae0636e5bf4afc0a0d |
| Self-Refine | 0 | Not recorded | 68fa7bd01e209131cea8aa62 |

### SRGen

Pass@1: 28. Result ID: 6a1d4d91fbc373592c16c481.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

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

### OXAFull

Pass@1: 26.6. Result ID: 69ba5fe747f34ce924a42e20.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"After RLVR (†)"}. This record does not assert independent reproduction.

### OXAMLE

Pass@1: 26.5. Result ID: 69ba5fe747f34ce924a42e1f.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"After RLVR (†)"}. This record does not assert independent reproduction.

### Self-Refine

Pass@1: 25.3. Result ID: 6a1d4d91fbc373592c16c480.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fc4.md>)

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

### OXAMLE

Pass@1: 24.5. Result ID: 69ba5fe747f34ce924a42e1b.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### SFT

Pass@1: 24.4. Result ID: 69ba5fe747f34ce924a42e1a.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### SFT

Pass@1: 23.6. Result ID: 69ba5fe747f34ce924a42e1e.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"After RLVR (†)"}. This record does not assert independent reproduction.

### CoT

Pass@1: 23.3. Result ID: 6a1d4d91fbc373592c16c47f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

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

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

### OXAFull

Pass@1: 23.1. Result ID: 69ba5fe747f34ce924a42e1c.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### SFTLP

Pass@1: 21.3. Result ID: 69ba5fe747f34ce924a42e1d.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"After RLVR (†)"}. This record does not assert independent reproduction.

### OXAMLE

Pass@1: 19.7. Result ID: 69ba5fe747f34ce924a42e16.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"After RLVR (†)"}. This record does not assert independent reproduction.

### SFTLP

Pass@1: 19.3. Result ID: 69ba5fe747f34ce924a42e19.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### SRGen

Pass@1: 19.3. Result ID: 6a1d4d91fbc373592c16c47b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

Recorded evaluation configuration: {"Model":"DS-R1-Qwen-7B"}. This record does not assert independent reproduction.

### OXAFull

Pass@1: 19.1. Result ID: 69ba5fe747f34ce924a42e17.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"After RLVR (†)"}. This record does not assert independent reproduction.

### OXAMLE

Pass@1: 18.5. Result ID: 69ba5fe747f34ce924a42e12.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### OXAFull

Pass@1: 18.2. Result ID: 69ba5fe747f34ce924a42e13.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### SRGen

Pass@1: 18. Result ID: 6a1d4d91fbc373592c16c47e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

Recorded evaluation configuration: {"Model":"DS-R1-Llama-8B"}. This record does not assert independent reproduction.

### Self-Refine

Pass@1: 16. Result ID: 6a1d4d91fbc373592c16c47d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fc4.md>)

Recorded evaluation configuration: {"Model":"DS-R1-Llama-8B"}. This record does not assert independent reproduction.

### CoT

Pass@1: 15.3. Result ID: 6a1d4d91fbc373592c16c479.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

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

Recorded evaluation configuration: {"Model":"DS-R1-Qwen-7B"}. This record does not assert independent reproduction.

### Self-Refine

Pass@1: 14.7. Result ID: 6a1d4d91fbc373592c16c47a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fc4.md>)

Recorded evaluation configuration: {"Model":"DS-R1-Qwen-7B"}. This record does not assert independent reproduction.

### CoT

Pass@1: 14. Result ID: 6a1d4d91fbc373592c16c47c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

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

Recorded evaluation configuration: {"Model":"DS-R1-Llama-8B"}. This record does not assert independent reproduction.

### SFT

Pass@1: 13.8. Result ID: 69ba5fe747f34ce924a42e15.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"After RLVR (†)"}. This record does not assert independent reproduction.

### SFT

Pass@1: 11.6. Result ID: 69ba5fe747f34ce924a42e11.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### SFTLP

Pass@1: 9.5. Result ID: 69ba5fe747f34ce924a42e14.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"After RLVR (†)"}. This record does not assert independent reproduction.

### SFTLP

Pass@1: 7.1. Result ID: 69ba5fe747f34ce924a42e10.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### SRGen

Pass@1: 3.3. Result ID: 6a1d4d91fbc373592c16c478.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction.

### CoT

Pass@1: 1.3. Result ID: 6a1d4d91fbc373592c16c476.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

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

Recorded evaluation configuration: {"Model":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction.

### Base

Pass@1: 0.6. Result ID: 69ba5fe747f34ce924a42e18.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-7B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### Base

Pass@1: 0.5. Result ID: 69ba5fe747f34ce924a42e0f.

[Reporting paper](<https://www.sota2.com/research/paper/69ba31ae0636e5bf4afc0a0d.md>)

Recorded evaluation configuration: {"Model Backbone":"Qwen2.5-1.5B-Math","RLVR Stage":"Before RLVR"}. This record does not assert independent reproduction.

### Self-Refine

Pass@1: 0. Result ID: 6a1d4d91fbc373592c16c477.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bd01e209131cea8aa62.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fc4.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-Math-7B"}. This record does not assert independent reproduction.

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