# Question Answering on GPQA-D (∆Acc, CR)

Source: [Question Answering on GPQA-D (∆Acc, CR)](<https://www.sota2.com/research/sota/question-answering-on-gpqa-d-acc-cr>)

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

Data updated: 2026-04-09T23:38:03.356Z

Evaluation of model performance on the 'D' domain/subset of the GPQA dataset for Question Answering, measured by Delta Accuracy (∆Acc) and Coverage Rate (CR).

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 | Question Answering |
| Dataset (including any stated split) | GPQA-D |
| Metric | Coverage Rate |
| 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

- [Coverage Rate](<https://www.sota2.com/research/sota/question-answering-on-gpqa-d-acc-cr.md?metric=Coverage%20Rate>): Higher is better; unit: PERCENT.

- [Delta Accuracy](<https://www.sota2.com/research/sota/question-answering-on-gpqa-d-acc-cr.md?metric=Delta%20Accuracy>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Coverage Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Vanilla | 100 | Not recorded | 69d7327f7d0172140ec76af9 |
| Vanilla | 100 | Not recorded | 69d7327f7d0172140ec76af9 |
| DEER | 84 | Not recorded | 69d7327f7d0172140ec76af9 |
| DEER-PRo | 84 | Not recorded | 69d7327f7d0172140ec76af9 |
| TCC | 61 | Not recorded | 69d7327f7d0172140ec76af9 |
| DEER-PRo | 55 | Not recorded | 69d7327f7d0172140ec76af9 |
| BAEE | 51 | Not recorded | 69d7327f7d0172140ec76af9 |
| Dynasor-CoT | 40 | Not recorded | 69d7327f7d0172140ec76af9 |
| DEER | 40 | Not recorded | 69d7327f7d0172140ec76af9 |
| BAEE | 33 | Not recorded | 69d7327f7d0172140ec76af9 |
| NoThinking | 32 | Not recorded | 69d7327f7d0172140ec76af9 |

### Vanilla

Coverage Rate: 100. Result ID: 69d8376f47f34ce924bffeb6.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"—","Base Model":"Qwen3-14B (DEER) / Qwen3-8B-Think (ours)"}. This record does not assert independent reproduction.

### Vanilla

Coverage Rate: 100. Result ID: 69d8376f47f34ce924bffebd.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"—","Base Model":"QwQ-32B (DEER) / Qwen3-32B-Think (ours)"}. This record does not assert independent reproduction.

### DEER

Coverage Rate: 84. Result ID: 69d8376f47f34ce924bffebe.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"semi-white","Base Model":"QwQ-32B (DEER) / Qwen3-32B-Think (ours)"}. This record does not assert independent reproduction.

### DEER-PRo

Coverage Rate: 84. Result ID: 69d8376f47f34ce924bffebf.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"semi-white","Base Model":"QwQ-32B (DEER) / Qwen3-32B-Think (ours)"}. This record does not assert independent reproduction.

### TCC

Coverage Rate: 61. Result ID: 69d8376f47f34ce924bffeb8.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"black-box","Base Model":"Qwen3-14B (DEER) / Qwen3-8B-Think (ours)"}. This record does not assert independent reproduction.

### DEER-PRo

Coverage Rate: 55. Result ID: 69d8376f47f34ce924bffebb.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"semi-white","Base Model":"Qwen3-14B (DEER) / Qwen3-8B-Think (ours)"}. This record does not assert independent reproduction.

### BAEE

Coverage Rate: 51. Result ID: 69d8376f47f34ce924bffebc.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

Recorded evaluation configuration: {"Access":"black-box","Base Model":"Qwen3-14B (DEER) / Qwen3-8B-Think (ours)"}. This record does not assert independent reproduction.

### Dynasor-CoT

Coverage Rate: 40. Result ID: 69d8376f47f34ce924bffeb9.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"black-box","Base Model":"Qwen3-14B (DEER) / Qwen3-8B-Think (ours)"}. This record does not assert independent reproduction.

### DEER

Coverage Rate: 40. Result ID: 69d8376f47f34ce924bffeba.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"semi-white","Base Model":"Qwen3-14B (DEER) / Qwen3-8B-Think (ours)"}. This record does not assert independent reproduction.

### BAEE

Coverage Rate: 33. Result ID: 69d8376f47f34ce924bffec0.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

Recorded evaluation configuration: {"Access":"black-box","Base Model":"QwQ-32B (DEER) / Qwen3-32B-Think (ours)"}. This record does not assert independent reproduction.

### NoThinking

Coverage Rate: 32. Result ID: 69d8376f47f34ce924bffeb7.

[Reporting paper](<https://www.sota2.com/research/paper/69d7327f7d0172140ec76af9.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba11e209131cea89778.md>)

Recorded evaluation configuration: {"Access":"black-box","Base Model":"Qwen3-14B (DEER) / Qwen3-8B-Think (ours)"}. This record does not assert independent reproduction.

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