# Question Answering on MMLU-Pro (test)

Source: [Question Answering on MMLU-Pro (test)](<https://www.sota2.com/research/sota/question-answering-on-mmlu-pro-test>)

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

Data updated: 2026-02-26T05:54:19.787Z

Evaluation of model performance on the MMLU-Pro test set, specifically tracking resource consumption metrics such as optimization-phase token usage.

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 | General question answering |
| Dataset (including any stated split) | MMLU-Pro (test) |
| Metric | Optimization Token Usage |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [Optimization Token Usage](<https://www.sota2.com/research/sota/question-answering-on-mmlu-pro-test.md?metric=Optimization%20Token%20Usage>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Optimization Token Usage | Result date | Report paper |
| --- | --- | --- | --- |
| ETGPO | 595 | Not recorded | 6981812ea8b01e76cc8e2315 |
| GEPA | 2623 | Not recorded | 6981812ea8b01e76cc8e2315 |
| MIPROv2 | 3859 | Not recorded | 6981812ea8b01e76cc8e2315 |

### ETGPO

Optimization Token Usage: 595. Result ID: 699610785698665ec44e16cc.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e2315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e2315.md>)

Recorded evaluation configuration: {"Backbone model":"GPT-4.1-mini","Optimizer":"GPT-4.1"}. This record does not assert independent reproduction.

### GEPA

Optimization Token Usage: 2623. Result ID: 699610785698665ec44e16cb.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e2315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a3a1e209131cea81ee3.md>)

Recorded evaluation configuration: {"Backbone model":"GPT-4.1-mini","Optimizer":"GPT-4.1"}. This record does not assert independent reproduction.

### MIPROv2

Optimization Token Usage: 3859. Result ID: 699610785698665ec44e16ca.

[Reporting paper](<https://www.sota2.com/research/paper/6981812ea8b01e76cc8e2315.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75121e209131cea65828.md>)

Recorded evaluation configuration: {"Backbone model":"GPT-4.1-mini","Optimizer":"GPT-4.1"}. This record does not assert independent reproduction.

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