# Fact Verification on AVERITEC

Source: [Fact Verification on AVERITEC](<https://www.sota2.com/research/sota/fact-verification-on-averitec>)

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

Data updated: 2026-02-26T05:30:34.372Z

Evaluation of model performance on the AVERITEC dataset for Fact Verification, reporting 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 | Fact Verification |
| Dataset (including any stated split) | AVERITEC |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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/fact-verification-on-averitec.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DRAG\_E | 49.1 | Not recorded | 68fa79031e209131cea7baa6 |
| DRAG\_C | 45.63 | Not recorded | 68fa79031e209131cea7baa6 |
| DRAG\_G | 40.98 | Not recorded | 68fa79031e209131cea7baa6 |
| DRAG\_E | 32.43 | Not recorded | 68fa79031e209131cea7baa6 |
| DRAG\_C | 32.29 | Not recorded | 68fa79031e209131cea7baa6 |
| DRAG\_G | 30.11 | Not recorded | 68fa79031e209131cea7baa6 |
| Original | 29 | Not recorded | 68fa79031e209131cea7baa6 |
| Original | 26 | Not recorded | 68fa79031e209131cea7baa6 |

### DRAG\_E

Accuracy: 49.1. Result ID: 6995b7053badfaffe6b7bb61.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Implementation](<https://github.com/VILA-Lab/DRAG>)

Recorded evaluation configuration: {"Student Model":"GPT-3.5-Turbo","Distillation Mode":"Evidence-based"}. This record does not assert independent reproduction.

### DRAG\_C

Accuracy: 45.63. Result ID: 6995b7053badfaffe6b7bb62.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Implementation](<https://github.com/VILA-Lab/DRAG>)

Recorded evaluation configuration: {"Student Model":"GPT-3.5-Turbo","Distillation Mode":"Combined (Graph and Evidence)"}. This record does not assert independent reproduction.

### DRAG\_G

Accuracy: 40.98. Result ID: 6995b7053badfaffe6b7bb60.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Implementation](<https://github.com/VILA-Lab/DRAG>)

Recorded evaluation configuration: {"Student Model":"GPT-3.5-Turbo","Distillation Mode":"Graph-based"}. This record does not assert independent reproduction.

### DRAG\_E

Accuracy: 32.43. Result ID: 6995b7053badfaffe6b7bb5d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Implementation](<https://github.com/VILA-Lab/DRAG>)

Recorded evaluation configuration: {"Student Model":"BLOOM-7b","Distillation Mode":"Evidence-based"}. This record does not assert independent reproduction.

### DRAG\_C

Accuracy: 32.29. Result ID: 6995b7053badfaffe6b7bb5e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Implementation](<https://github.com/VILA-Lab/DRAG>)

Recorded evaluation configuration: {"Student Model":"BLOOM-7b","Distillation Mode":"Combined (Graph and Evidence)"}. This record does not assert independent reproduction.

### DRAG\_G

Accuracy: 30.11. Result ID: 6995b7053badfaffe6b7bb5c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

[Implementation](<https://github.com/VILA-Lab/DRAG>)

Recorded evaluation configuration: {"Student Model":"BLOOM-7b","Distillation Mode":"Graph-based"}. This record does not assert independent reproduction.

### Original

Accuracy: 29. Result ID: 6995b7053badfaffe6b7bb5f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

Recorded evaluation configuration: {"Student Model":"GPT-3.5-Turbo"}. This record does not assert independent reproduction.

### Original

Accuracy: 26. Result ID: 6995b7053badfaffe6b7bb5b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa79031e209131cea7baa6.md>)

Recorded evaluation configuration: {"Student Model":"BLOOM-7b"}. This record does not assert independent reproduction.

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