# Document Reranking on FEVER

Source: [Document Reranking on FEVER](<https://www.sota2.com/research/sota/document-reranking-on-fever>)

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

Data updated: 2026-06-17T07:00:37.806Z

Evaluation of Document Reranking performance on the FEVER dataset, measured using NDCG@5 and percentage change (Δ%).

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 | Document Reranking |
| Dataset (including any stated split) | FEVER |
| Metric | NDCG@5 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 19 of 19 |
| 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

- [NDCG@5](<https://www.sota2.com/research/sota/document-reranking-on-fever.md?metric=NDCG%405>): Higher is better; unit: PERCENT.

- [Percentage Change (Δ%)](<https://www.sota2.com/research/sota/document-reranking-on-fever.md?metric=Percentage%20Change%20(%CE%94%25)>): Higher is better; unit: PERCENT.

- [Recall@5](<https://www.sota2.com/research/sota/document-reranking-on-fever.md?metric=Recall%405>): Higher is better; unit: PERCENT.

- [F1@τ](<https://www.sota2.com/research/sota/document-reranking-on-fever.md?metric=F1%40%CF%84>): Higher is better; unit: PERCENT.

## Recorded results

| Method | NDCG@5 | Result date | Report paper |
| --- | --- | --- | --- |
| MonoT5-3B | 100 | Not recorded | 6a322a3ad33dfb23e783ec6d |
| Qwen3-Reranker-8B | 100 | Not recorded | 6a322a3ad33dfb23e783ec6d |
| MonoT5-base | 99.9 | Not recorded | 6a322a3ad33dfb23e783ec6d |
| LLM2Vec-Gen | 99.7 | Not recorded | 6a322a3ad33dfb23e783ec6d |
| RSRank | 99.2 | Not recorded | 6a322a3ad33dfb23e783ec6d |
| RankT5 | 81.556 | Not recorded | 69fc1cac5497b3b670c88615 |
| RankT5 + CAR | 81.556 | Not recorded | 69fc1cac5497b3b670c88615 |
| Cross-Encoder | 78.457 | Not recorded | 69fc1cac5497b3b670c88615 |
| Cross-Encoder + CAR | 78.457 | Not recorded | 69fc1cac5497b3b670c88615 |
| ColBERT | 76.169 | Not recorded | 69fc1cac5497b3b670c88615 |
| ColBERT + CAR | 76.169 | Not recorded | 69fc1cac5497b3b670c88615 |
| RankGPT | 74.268 | Not recorded | 69fc1cac5497b3b670c88615 |
| RankGPT + CAR | 74.268 | Not recorded | 69fc1cac5497b3b670c88615 |
| Contriever | 74.253 | Not recorded | 69fc1cac5497b3b670c88615 |
| Contriever + CAR | 74.253 | Not recorded | 69fc1cac5497b3b670c88615 |
| QLM + CAR | 57.82 | Not recorded | 69fc1cac5497b3b670c88615 |
| QLM | 55.687 | Not recorded | 69fc1cac5497b3b670c88615 |
| YesNo + CAR | 41.326 | Not recorded | 69fc1cac5497b3b670c88615 |
| YesNo | 25.462 | Not recorded | 69fc1cac5497b3b670c88615 |

### MonoT5-3B

NDCG@5: 100. Result ID: 6a3245fdfbc373592c2f3eac.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a3ad33dfb23e783ec6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67341e209131cea14b55.md>)

[Implementation](<http://anserini.io/>)

Recorded evaluation configuration: {"Threshold (τ)":"0.5"}. This record does not assert independent reproduction.

### Qwen3-Reranker-8B

NDCG@5: 100. Result ID: 6a3245fdfbc373592c2f3eae.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a3ad33dfb23e783ec6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79601e209131cea7d516.md>)

Recorded evaluation configuration: {"Threshold (τ)":"0.5"}. This record does not assert independent reproduction.

### MonoT5-base

NDCG@5: 99.9. Result ID: 6a3245fdfbc373592c2f3eab.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a3ad33dfb23e783ec6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67341e209131cea14b55.md>)

[Implementation](<http://anserini.io/>)

Recorded evaluation configuration: {"Model Parameters":"0.2B","Threshold (τ)":"0.5"}. This record does not assert independent reproduction.

### LLM2Vec-Gen

NDCG@5: 99.7. Result ID: 6a3245fdfbc373592c2f3ead.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a3ad33dfb23e783ec6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b24890d030084c22e2f8f8.md>)

[Implementation](<https://github.com/McGill-NLP/llm2vec-gen>)

Recorded evaluation configuration: {"Base Model":"Qwen3-8B","Threshold (τ)":"0"}. This record does not assert independent reproduction.

### RSRank

NDCG@5: 99.2. Result ID: 6a3245fdfbc373592c2f3eaf.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a3ad33dfb23e783ec6d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a3ad33dfb23e783ec6d.md>)

Recorded evaluation configuration: {"Threshold (τ)":"0"}. This record does not assert independent reproduction.

### RankT5

NDCG@5: 81.556. Result ID: 69fc4cf947f34ce924deff50.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"Retriever":"Contriever","Category":"Supervised Neural Reranker"}. This record does not assert independent reproduction.

### RankT5 + CAR

NDCG@5: 81.556. Result ID: 69fc4cf947f34ce924deff51.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"Retriever":"Contriever","Category":"Supervised Neural Reranker","Confidence-Aware Reranking":"Enabled"}. This record does not assert independent reproduction.

### Cross-Encoder

NDCG@5: 78.457. Result ID: 69fc4cf947f34ce924deff4e.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"Retriever":"Contriever","Category":"Supervised Neural Reranker"}. This record does not assert independent reproduction.

### Cross-Encoder + CAR

NDCG@5: 78.457. Result ID: 69fc4cf947f34ce924deff4f.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"Retriever":"Contriever","Category":"Supervised Neural Reranker","Confidence-Aware Reranking":"Enabled"}. This record does not assert independent reproduction.

### ColBERT

NDCG@5: 76.169. Result ID: 69fc4cf947f34ce924deff4c.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"Retriever":"Contriever","Category":"Supervised Neural Reranker"}. This record does not assert independent reproduction.

### ColBERT + CAR

NDCG@5: 76.169. Result ID: 69fc4cf947f34ce924deff4d.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"Retriever":"Contriever","Category":"Supervised Neural Reranker","Confidence-Aware Reranking":"Enabled"}. This record does not assert independent reproduction.

### RankGPT

NDCG@5: 74.268. Result ID: 69fc4cf947f34ce924deff4a.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-7B-Instruct","Retriever":"Contriever","Category":"LLM-based Reranker"}. This record does not assert independent reproduction.

### RankGPT + CAR

NDCG@5: 74.268. Result ID: 69fc4cf947f34ce924deff4b.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-7B-Instruct","Retriever":"Contriever","Category":"LLM-based Reranker","Confidence-Aware Reranking":"Enabled"}. This record does not assert independent reproduction.

### Contriever

NDCG@5: 74.253. Result ID: 69fc4cf947f34ce924deff44.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d4b1e209131cea38d50.md>)

[Implementation](<https://github.com/facebookresearch/contriever>)

Recorded evaluation configuration: {"Retriever":"Contriever","Category":"Retriever Only"}. This record does not assert independent reproduction.

### Contriever + CAR

NDCG@5: 74.253. Result ID: 69fc4cf947f34ce924deff45.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"Retriever":"Contriever","Category":"Retriever Only","Confidence-Aware Reranking":"Enabled"}. This record does not assert independent reproduction.

### QLM + CAR

NDCG@5: 57.82. Result ID: 69fc4cf947f34ce924deff49.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-7B-Instruct","Retriever":"Contriever","Category":"LLM-based Reranker","Confidence-Aware Reranking":"Enabled"}. This record does not assert independent reproduction.

### QLM

NDCG@5: 55.687. Result ID: 69fc4cf947f34ce924deff48.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-7B-Instruct","Retriever":"Contriever","Category":"LLM-based Reranker"}. This record does not assert independent reproduction.

### YesNo + CAR

NDCG@5: 41.326. Result ID: 69fc4cf947f34ce924deff47.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-7B-Instruct","Retriever":"Contriever","Category":"LLM-based Reranker","Confidence-Aware Reranking":"Enabled"}. This record does not assert independent reproduction.

### YesNo

NDCG@5: 25.462. Result ID: 69fc4cf947f34ce924deff46.

[Reporting paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69fc1cac5497b3b670c88615.md>)

Recorded evaluation configuration: {"LLM":"Qwen2.5-7B-Instruct","Retriever":"Contriever","Category":"LLM-based Reranker"}. This record does not assert independent reproduction.

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