# Information Retrieval on TREC-COVID BEIR

Source: [Information Retrieval on TREC-COVID BEIR](<https://www.sota2.com/research/sota/information-retrieval-on-trec-covid-beir>)

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

Data updated: 2026-06-11T08:08:28.658Z

Evaluation of Information Retrieval performance on the TREC-COVID BEIR benchmark setup, typically measured using NDCG@10.

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 | Information Retrieval |
| Dataset (including any stated split) | TREC-COVID BEIR |
| Metric | NDCG@10 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 27 of 27 |
| 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@10](<https://www.sota2.com/research/sota/information-retrieval-on-trec-covid-beir.md?metric=NDCG%4010>): Higher is better; unit: PERCENT.

## Recorded results

| Method | NDCG@10 | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen3-8B | 95 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| Qwen3-4B | 92.9 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| Qwen3-0.6B | 90.5 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| e5-large-inst | 82.5 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| STORM | 79.6 | Not recorded | 6a28f37190966ade919c1930 |
| bge-en-icl | 79.1 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| bge-large | 75.4 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| GenQRE | 75.3 | Not recorded | 6a28f37190966ade919c1930 |
| inf-v1 | 75.1 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| Splade-V3 | 74.8 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| bge-lg-v1.5 | 74.7 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| Q2D | 74.3 | Not recorded | 6a28f37190966ade919c1930 |
| MILCO | 74 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| opensearch-gte | 73.3 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| gte-base-v1.5 | 73.1 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| inf-v1-1.5b | 72.4 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| Q2K | 71.5 | Not recorded | 6a28f37190966ade919c1930 |
| MUGI | 71.4 | Not recorded | 6a28f37190966ade919c1930 |
| e5-large | 71.2 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| QA-Expa | 70.7 | Not recorded | 6a28f37190966ade919c1930 |
| gte-large | 70.2 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| LameR | 70.2 | Not recorded | 6a28f37190966ade919c1930 |
| CSQE | 69.9 | Not recorded | 6a28f37190966ade919c1930 |
| LENS-d4K | 69.7 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| gte-base | 68.8 | Not recorded | 68fa7bc41e209131cea8a4c0 |
| GenQR | 68.7 | Not recorded | 6a28f37190966ade919c1930 |
| RM3 | 59.3 | Not recorded | 6a28f37190966ade919c1930 |

### Qwen3-8B

NDCG@10: 95. Result ID: 69bd171147f34ce924a79468.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

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

Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction.

### Qwen3-4B

NDCG@10: 92.9. Result ID: 69bd171147f34ce924a7946a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

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

Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction.

### Qwen3-0.6B

NDCG@10: 90.5. Result ID: 69bd171147f34ce924a79475.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

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

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### e5-large-inst

NDCG@10: 82.5. Result ID: 69bd171147f34ce924a7946c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72251e209131cea54c85.md>)

Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction.

### STORM

NDCG@10: 79.6. Result ID: 6a2a6ce5fbc373592c276407.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

Recorded evaluation configuration: {"Backbone":"Qwen3-8B","Max tokens":"64"}. This record does not assert independent reproduction.

### bge-en-icl

NDCG@10: 79.1. Result ID: 69bd171147f34ce924a79469.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74e51e209131cea6483e.md>)

Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction.

### bge-large

NDCG@10: 75.4. Result ID: 69bd171147f34ce924a79471.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### GenQRE

NDCG@10: 75.3. Result ID: 6a2a6ce5fbc373592c276400.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72d41e209131cea58c67.md>)

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

### inf-v1

NDCG@10: 75.1. Result ID: 69bd171147f34ce924a7946f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### Splade-V3

NDCG@10: 74.8. Result ID: 69bd171147f34ce924a79477.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72751e209131cea567ad.md>)

[Implementation](<https://github.com/naver/splade>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### bge-lg-v1.5

NDCG@10: 74.7. Result ID: 69bd171147f34ce924a79474.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### Q2D

NDCG@10: 74.3. Result ID: 6a2a6ce5fbc373592c276403.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70d71e209131cea4d93f.md>)

Recorded evaluation configuration: {"Backbone":"GPT-4.1","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### MILCO

NDCG@10: 74. Result ID: 69bd171147f34ce924a79478.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### opensearch-gte

NDCG@10: 73.3. Result ID: 69bd171147f34ce924a79476.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### gte-base-v1.5

NDCG@10: 73.1. Result ID: 69bd171147f34ce924a79472.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### inf-v1-1.5b

NDCG@10: 72.4. Result ID: 69bd171147f34ce924a7946b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction.

### Q2K

NDCG@10: 71.5. Result ID: 6a2a6ce5fbc373592c276402.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f491e209131cea44ca0.md>)

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

### MUGI

NDCG@10: 71.4. Result ID: 6a2a6ce5fbc373592c276405.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73ef1e209131cea5ef6d.md>)

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

### e5-large

NDCG@10: 71.2. Result ID: 69bd171147f34ce924a79473.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72251e209131cea54c85.md>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### QA-Expa

NDCG@10: 70.7. Result ID: 6a2a6ce5fbc373592c276401.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f491e209131cea44ca0.md>)

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

### gte-large

NDCG@10: 70.2. Result ID: 69bd171147f34ce924a7946d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73611e209131cea5c103.md>)

Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction.

### LameR

NDCG@10: 70.2. Result ID: 6a2a6ce5fbc373592c276404.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

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

### CSQE

NDCG@10: 69.9. Result ID: 6a2a6ce5fbc373592c276406.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72541e209131cea55af7.md>)

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

### LENS-d4K

NDCG@10: 69.7. Result ID: 69bd171147f34ce924a7946e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

Recorded evaluation configuration: {"Model Size Category":"\>=1B parameters"}. This record does not assert independent reproduction.

### gte-base

NDCG@10: 68.8. Result ID: 69bd171147f34ce924a79470.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7bc41e209131cea8a4c0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73611e209131cea5c103.md>)

Recorded evaluation configuration: {"Model Size Category":"\<1B parameters"}. This record does not assert independent reproduction.

### GenQR

NDCG@10: 68.7. Result ID: 6a2a6ce5fbc373592c2763ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703c1e209131cea49d67.md>)

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

### RM3

NDCG@10: 59.3. Result ID: 6a2a6ce5fbc373592c2763fe.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37190966ade919c1930.md>)

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

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