# Mathematical Reasoning on AIME 24 (Pass@1, TPS, Latency)

Source: [Mathematical Reasoning on AIME 24 (Pass@1, TPS, Latency)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-pass-at-1-tps-latency>)

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

Data updated: 2026-02-26T05:57:24.337Z

Evaluation of model performance on the AIME 2024 dataset for mathematical reasoning, reporting accuracy via Pass@1, throughput (TPS), and inference latency.

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) | AIME 24 |
| Metric | Pass@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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-aime-24-pass-at-1-tps-latency.md?metric=Pass%401>): Higher is better; unit: PERCENT.

- [TPS](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-pass-at-1-tps-latency.md?metric=TPS>): Higher is better; unit: SCALAR.

- [Latency (ms)](<https://www.sota2.com/research/sota/mathematical-reasoning-on-aime-24-pass-at-1-tps-latency.md?metric=Latency%20(ms)>): Lower is better; unit: TIME.

## Recorded results

| Method | Pass@1 | Result date | Report paper |
| --- | --- | --- | --- |
| Target Model | 63 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| Target Model | 62.1 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| SpecReason | 61 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| SemanticSpec | 61 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| SemanticSpec | 55.3 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| SpecSampling | 54 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| SpecReason | 47 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| SpecSampling | 44.3 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| SpecThinking | 24.1 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| Draft Model | 23.3 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| Draft Model | 23.3 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |
| SpecThinking | 20.4 | Not recorded | 6982d2f5a8b01e76cc8e99a0 |

### Target Model

Pass@1: 63. Result ID: 69964ebb5698665ec4935f26.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction.

### Target Model

Pass@1: 62.1. Result ID: 69964ebb5698665ec4935f20.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction.

### SpecReason

Pass@1: 61. Result ID: 69964ebb5698665ec4935f27.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78961e209131cea791f9.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction.

### SemanticSpec

Pass@1: 61. Result ID: 69964ebb5698665ec4935f2a.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction.

### SemanticSpec

Pass@1: 55.3. Result ID: 69964ebb5698665ec4935f24.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction.

### SpecSampling

Pass@1: 54. Result ID: 69964ebb5698665ec4935f29.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6f1e209131cea458d8.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction.

### SpecReason

Pass@1: 47. Result ID: 69964ebb5698665ec4935f21.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78961e209131cea791f9.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction.

### SpecSampling

Pass@1: 44.3. Result ID: 69964ebb5698665ec4935f23.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f6f1e209131cea458d8.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction.

### SpecThinking

Pass@1: 24.1. Result ID: 69964ebb5698665ec4935f22.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa780a1e209131cea767b6.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction.

### Draft Model

Pass@1: 23.3. Result ID: 69964ebb5698665ec4935f1f.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"DeepseekR1-32B"}. This record does not assert independent reproduction.

### Draft Model

Pass@1: 23.3. Result ID: 69964ebb5698665ec4935f25.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction.

### SpecThinking

Pass@1: 20.4. Result ID: 69964ebb5698665ec4935f28.

[Reporting paper](<https://www.sota2.com/research/paper/6982d2f5a8b01e76cc8e99a0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa780a1e209131cea767b6.md>)

Recorded evaluation configuration: {"Draft Model":"DeepseekR1-1.5B","Target Model":"QwQ-32B"}. This record does not assert independent reproduction.

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