# Selective Question Answering on AbstainQA (val)

Source: [Selective Question Answering on AbstainQA (val)](<https://www.sota2.com/research/sota/selective-question-answering-on-abstainqa-val>)

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

Data updated: 2026-05-29T08:33:03.609Z

Evaluation of model performance on the validation split of the AbstainQA dataset, focusing on the Selective Question Answering task, measured by accuracy.

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 | Selective Question Answering |
| Dataset (including any stated split) | AbstainQA (val) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 11 of 11 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/selective-question-answering-on-abstainqa-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Single Best | 21 | Not recorded | 6a191daddbd7150506f82926 |
| Base | 18.5 | Not recorded | 6a191daddbd7150506f82926 |
| EvoGM | 16.5 | Not recorded | 6a191daddbd7150506f82926 |
| CMA | 14 | Not recorded | 6a191daddbd7150506f82926 |
| PSO-Merging | 13 | Not recorded | 6a191daddbd7150506f82926 |
| Model Swarm | 13 | Not recorded | 6a191daddbd7150506f82926 |
| DARE | 9.5 | Not recorded | 6a191daddbd7150506f82926 |
| Task Arithmetic | 7.5 | Not recorded | 6a191daddbd7150506f82926 |
| TIES | 7.5 | Not recorded | 6a191daddbd7150506f82926 |
| Model Soup | 7 | Not recorded | 6a191daddbd7150506f82926 |
| MTL | 0.5 | Not recorded | 6a191daddbd7150506f82926 |

### Single Best

Accuracy: 21. Result ID: 6a194e9bfbc373592c13a8b6.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### Base

Accuracy: 18.5. Result ID: 6a194e9bfbc373592c13a8b4.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### EvoGM

Accuracy: 16.5. Result ID: 6a194e9bfbc373592c13a8be.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### CMA

Accuracy: 14. Result ID: 6a194e9bfbc373592c13a8bb.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76b81e209131cea6eb82.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### PSO-Merging

Accuracy: 13. Result ID: 6a194e9bfbc373592c13a8bc.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af41e209131cea85f56.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### Model Swarm

Accuracy: 13. Result ID: 6a194e9bfbc373592c13a8bd.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79061e209131cea7bc34.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### DARE

Accuracy: 9.5. Result ID: 6a194e9bfbc373592c13a8ba.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73921e209131cea5d4aa.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### Task Arithmetic

Accuracy: 7.5. Result ID: 6a194e9bfbc373592c13a8b8.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ef01e209131cea43012.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### TIES

Accuracy: 7.5. Result ID: 6a194e9bfbc373592c13a8b9.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71091e209131cea4ecd8.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### Model Soup

Accuracy: 7. Result ID: 6a194e9bfbc373592c13a8b7.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ce11e209131cea3679c.md>)

[Implementation](<https://github.com/mlfoundations/model-soups>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

### MTL

Accuracy: 0.5. Result ID: 6a194e9bfbc373592c13a8b5.

[Reporting paper](<https://www.sota2.com/research/paper/6a191daddbd7150506f82926.md>)

Recorded evaluation configuration: {"Base model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

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