# Math Information Retrieval on ARQMath 2 (test)

Source: [Math Information Retrieval on ARQMath 2 (test)](<https://www.sota2.com/research/sota/math-information-retrieval-on-arqmath-2-test>)

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

Data updated: 2026-02-26T05:53:03.326Z

Evaluation of model performance on the test split of the ARQMath 2 dataset for Math Information Retrieval, typically measured using ranking metrics such as NDCG, MAP, and BPref.

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 | Math Information Retrieval |
| Dataset (including any stated split) | ARQMath 2 (test) |
| Metric | NDCG |
| 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

- [NDCG](<https://www.sota2.com/research/sota/math-information-retrieval-on-arqmath-2-test.md?metric=NDCG>): Higher is better; unit: PERCENT.

- [MAP](<https://www.sota2.com/research/sota/math-information-retrieval-on-arqmath-2-test.md?metric=MAP>): Higher is better; unit: PERCENT.

- [P@10](<https://www.sota2.com/research/sota/math-information-retrieval-on-arqmath-2-test.md?metric=P%4010>): Higher is better; unit: PERCENT.

- [BPref](<https://www.sota2.com/research/sota/math-information-retrieval-on-arqmath-2-test.md?metric=BPref>): Higher is better; unit: PERCENT.

## Recorded results

| Method | NDCG | Result date | Report paper |
| --- | --- | --- | --- |
| Approach0 + ColBERT | 44.7 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| MathDowsers Primary | 43.4 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| Approach0 + DPR | 42.9 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| DPRL QASim | 38.8 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| Approach0 + ColBERT | 38.3 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| Approach0 | 38.1 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| TU\_DBS Primary | 37.7 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| Approach0 + DPR | 37.2 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| MIRMU WIBC | 33.2 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| tf-idf+Tangent-S | 20.1 | Not recorded | 68fa6dbe1e209131cea3bca8 |
| tf-idf (Terrier) | 18.5 | Not recorded | 68fa6dbe1e209131cea3bca8 |

### Approach0 + ColBERT

NDCG: 44.7. Result ID: 698fe35a3a6c314849fc9507.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

[Implementation](<https://github.com/approach0/math-dense-retrievers/tree/emnlp2022>)

Recorded evaluation configuration: {"Category":"End-to-end fusion"}. This record does not assert independent reproduction.

### MathDowsers Primary

NDCG: 43.4. Result ID: 698fe35a3a6c314849fc94fd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

Recorded evaluation configuration: {"Category":"Previous systems"}. This record does not assert independent reproduction.

### Approach0 + DPR

NDCG: 42.9. Result ID: 698fe35a3a6c314849fc9506.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

[Implementation](<https://github.com/approach0/math-dense-retrievers/tree/emnlp2022>)

Recorded evaluation configuration: {"Category":"End-to-end fusion"}. This record does not assert independent reproduction.

### DPRL QASim

NDCG: 38.8. Result ID: 698fe35a3a6c314849fc94ff.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

Recorded evaluation configuration: {"Category":"Previous systems"}. This record does not assert independent reproduction.

### Approach0 + ColBERT

NDCG: 38.3. Result ID: 698fe35a3a6c314849fc9505.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

[Implementation](<https://github.com/approach0/math-dense-retrievers/tree/emnlp2022>)

Recorded evaluation configuration: {"Category":"Reranking"}. This record does not assert independent reproduction.

### Approach0

NDCG: 38.1. Result ID: 698fe35a3a6c314849fc9503.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

Recorded evaluation configuration: {"Category":"Structure search baseline"}. This record does not assert independent reproduction.

### TU\_DBS Primary

NDCG: 37.7. Result ID: 698fe35a3a6c314849fc94fe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

Recorded evaluation configuration: {"Category":"Previous systems"}. This record does not assert independent reproduction.

### Approach0 + DPR

NDCG: 37.2. Result ID: 698fe35a3a6c314849fc9504.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

[Implementation](<https://github.com/approach0/math-dense-retrievers/tree/emnlp2022>)

Recorded evaluation configuration: {"Category":"Reranking"}. This record does not assert independent reproduction.

### MIRMU WIBC

NDCG: 33.2. Result ID: 698fe35a3a6c314849fc9500.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

Recorded evaluation configuration: {"Category":"Previous systems"}. This record does not assert independent reproduction.

### tf-idf+Tangent-S

NDCG: 20.1. Result ID: 698fe35a3a6c314849fc9502.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

Recorded evaluation configuration: {"Category":"Previous systems"}. This record does not assert independent reproduction.

### tf-idf (Terrier)

NDCG: 18.5. Result ID: 698fe35a3a6c314849fc9501.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbe1e209131cea3bca8.md>)

Recorded evaluation configuration: {"Category":"Previous systems"}. This record does not assert independent reproduction.

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