# Mathematical Reasoning on In-Distribution Reasoning Suite (AIME 24, AIME 25, AMC, MATH-500, Minerva)

Source: [Mathematical Reasoning on In-Distribution Reasoning Suite (AIME 24, AIME 25, AMC, MATH-500, Minerva)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-in-distribution-reasoning-suite-aime-24-aime-25-amc-math-500-minerva>)

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

Data updated: 2026-04-13T08:19:49.087Z

Evaluation of Mathematical Reasoning performance across a specific suite including AIME 2024, AIME 2025, AMC, MATH-500, and Minerva components, utilizing Pass@k 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) | In-Distribution Reasoning Suite (AIME 24, AIME 25, AMC, MATH-500, Minerva) |
| Metric | AIME 24 Pass@32 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 14 of 14 |
| 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

- [AIME 24 Pass@32](<https://www.sota2.com/research/sota/mathematical-reasoning-on-in-distribution-reasoning-suite-aime-24-aime-25-amc-math-500-minerva.md?metric=AIME%2024%20Pass%4032>): Higher is better; unit: PERCENT.

- [AIME 25 Pass@32](<https://www.sota2.com/research/sota/mathematical-reasoning-on-in-distribution-reasoning-suite-aime-24-aime-25-amc-math-500-minerva.md?metric=AIME%2025%20Pass%4032>): Higher is better; unit: PERCENT.

- [AMC Pass@32](<https://www.sota2.com/research/sota/mathematical-reasoning-on-in-distribution-reasoning-suite-aime-24-aime-25-amc-math-500-minerva.md?metric=AMC%20Pass%4032>): Higher is better; unit: PERCENT.

- [MATH-500 Pass@1](<https://www.sota2.com/research/sota/mathematical-reasoning-on-in-distribution-reasoning-suite-aime-24-aime-25-amc-math-500-minerva.md?metric=MATH-500%20Pass%401>): Higher is better; unit: PERCENT.

- [Minerva Pass@1](<https://www.sota2.com/research/sota/mathematical-reasoning-on-in-distribution-reasoning-suite-aime-24-aime-25-amc-math-500-minerva.md?metric=Minerva%20Pass%401>): Higher is better; unit: PERCENT.

- [Average Pass Rate](<https://www.sota2.com/research/sota/mathematical-reasoning-on-in-distribution-reasoning-suite-aime-24-aime-25-amc-math-500-minerva.md?metric=Average%20Pass%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | AIME 24 Pass@32 | Result date | Report paper |
| --- | --- | --- | --- |
| DYPO | 36 | Not recorded | 69dc785a7d0172140ec788bd |
| Oat-Zero | 33.4 | Not recorded | 69dc785a7d0172140ec788bd |
| CHORD | 31.2 | Not recorded | 69dc785a7d0172140ec788bd |
| SRFT | 30.7 | Not recorded | 69dc785a7d0172140ec788bd |
| LUFFY | 29.4 | Not recorded | 69dc785a7d0172140ec788bd |
| ReLIFT | 28.3 | Not recorded | 69dc785a7d0172140ec788bd |
| SuperRL | 28.1 | Not recorded | 69dc785a7d0172140ec788bd |
| SimpleRL-Zero | 27 | Not recorded | 69dc785a7d0172140ec788bd |
| SFT → RL | 25.8 | Not recorded | 69dc785a7d0172140ec788bd |
| RL | 25.1 | Not recorded | 69dc785a7d0172140ec788bd |
| SFT | 22.2 | Not recorded | 69dc785a7d0172140ec788bd |
| PRIME-Zero | 17 | Not recorded | 69dc785a7d0172140ec788bd |
| OpenReasoner-Zero | 16.5 | Not recorded | 69dc785a7d0172140ec788bd |
| Qwen2.5-Math-7B | 11.5 | Not recorded | 69dc785a7d0172140ec788bd |

### DYPO

AIME 24 Pass@32: 36. Result ID: 69dca5cc47f34ce924c383a7.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

Recorded evaluation configuration: {"Training Category":"SFT and RL","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### Oat-Zero

AIME 24 Pass@32: 33.4. Result ID: 69dca5cc47f34ce924c383a0.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be51e209131cea8b201.md>)

Recorded evaluation configuration: {"Training Category":"Reinforcement Learning","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### CHORD

AIME 24 Pass@32: 31.2. Result ID: 69dca5cc47f34ce924c383a6.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bfc1e209131cea8ba85.md>)

Recorded evaluation configuration: {"Training Category":"SFT and RL","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### SRFT

AIME 24 Pass@32: 30.7. Result ID: 69dca5cc47f34ce924c383a5.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79ab1e209131cea7ecd7.md>)

Recorded evaluation configuration: {"Training Category":"SFT and RL","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### LUFFY

AIME 24 Pass@32: 29.4. Result ID: 69dca5cc47f34ce924c383a3.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79961e209131cea7e682.md>)

Recorded evaluation configuration: {"Training Category":"SFT and RL","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### ReLIFT

AIME 24 Pass@32: 28.3. Result ID: 69dca5cc47f34ce924c383a4.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7be61e209131cea8b28c.md>)

Recorded evaluation configuration: {"Training Category":"SFT and RL","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### SuperRL

AIME 24 Pass@32: 28.1. Result ID: 69dca5cc47f34ce924c383a2.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a851e209131cea83abd.md>)

Recorded evaluation configuration: {"Training Category":"SFT and RL","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### SimpleRL-Zero

AIME 24 Pass@32: 27. Result ID: 69dca5cc47f34ce924c3839d.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a721e209131cea8345b.md>)

Recorded evaluation configuration: {"Training Category":"Reinforcement Learning","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### SFT → RL

AIME 24 Pass@32: 25.8. Result ID: 69dca5cc47f34ce924c383a1.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa701f1e209131cea492fe.md>)

[Implementation](<https://github.com/facebookresearch/llama>)

Recorded evaluation configuration: {"Training Category":"SFT and RL","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### RL

AIME 24 Pass@32: 25.1. Result ID: 69dca5cc47f34ce924c3839c.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf71e209131cea314c0.md>)

[Implementation](<https://github.com/openai/following-instructions-human-feedback>)

Recorded evaluation configuration: {"Training Category":"Reinforcement Learning","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### SFT

AIME 24 Pass@32: 22.2. Result ID: 69dca5cc47f34ce924c3839b.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c131e209131cea31f71.md>)

Recorded evaluation configuration: {"Training Category":"Supervised Fine-Tuning","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### PRIME-Zero

AIME 24 Pass@32: 17. Result ID: 69dca5cc47f34ce924c3839f.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b9f1e209131cea8965d.md>)

Recorded evaluation configuration: {"Training Category":"Reinforcement Learning","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### OpenReasoner-Zero

AIME 24 Pass@32: 16.5. Result ID: 69dca5cc47f34ce924c3839e.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79d91e209131cea7fba6.md>)

Recorded evaluation configuration: {"Training Category":"Reinforcement Learning","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

### Qwen2.5-Math-7B

AIME 24 Pass@32: 11.5. Result ID: 69dca5cc47f34ce924c3839a.

[Reporting paper](<https://www.sota2.com/research/paper/69dc785a7d0172140ec788bd.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa767e1e209131cea6d6a7.md>)

Recorded evaluation configuration: {"Training Category":"Base Model","Backbone":"Qwen2.5-Math-7B","Inference Temperature":"0.6","Option Shuffling":"true"}. This record does not assert independent reproduction.

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