# Question Answering on MS-MARCO (ASR, RSR, PPL)

Source: [Question Answering on MS-MARCO (ASR, RSR, PPL)](<https://www.sota2.com/research/sota/question-answering-on-ms-marco-asr-rsr-ppl>)

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

Data updated: 2026-04-10T06:48:32.181Z

Evaluation of Question Answering performance on the MS-MARCO dataset, specifically measured using Accuracy, Recall, and Perplexity metrics.

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) | MS-MARCO |
| Metric | ASR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 35 of 35 |
| 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

- [ASR](<https://www.sota2.com/research/sota/question-answering-on-ms-marco-asr-rsr-ppl.md?metric=ASR>): Higher is better; unit: PERCENT.

- [RSR](<https://www.sota2.com/research/sota/question-answering-on-ms-marco-asr-rsr-ppl.md?metric=RSR>): Higher is better; unit: PERCENT.

- [PPL](<https://www.sota2.com/research/sota/question-answering-on-ms-marco-asr-rsr-ppl.md?metric=PPL>): Lower is better; unit: SCALAR.

## Recorded results

| Method | ASR | Result date | Report paper |
| --- | --- | --- | --- |
| AuthChain | 85 | Not recorded | 68fa7af71e209131cea86070 |
| AuthChain | 84 | Not recorded | 68fa7af71e209131cea86070 |
| AuthChain | 84 | Not recorded | 68fa7af71e209131cea86070 |
| AuthChain | 83 | Not recorded | 68fa7af71e209131cea86070 |
| AuthChain | 79 | Not recorded | 68fa7af71e209131cea86070 |
| AuthChain | 74 | Not recorded | 68fa7af71e209131cea86070 |
| Authority | 69 | Not recorded | 68fa7af71e209131cea86070 |
| Authority | 67 | Not recorded | 68fa7af71e209131cea86070 |
| Authority | 64 | Not recorded | 68fa7af71e209131cea86070 |
| CoE | 62 | Not recorded | 68fa7af71e209131cea86070 |
| CoE | 62 | Not recorded | 68fa7af71e209131cea86070 |
| CoE | 61 | Not recorded | 68fa7af71e209131cea86070 |
| PRAG | 57 | Not recorded | 68fa7af71e209131cea86070 |
| CoE | 54 | Not recorded | 68fa7af71e209131cea86070 |
| PRAG | 54 | Not recorded | 68fa7af71e209131cea86070 |
| Authority | 53 | Not recorded | 68fa7af71e209131cea86070 |
| CoE | 52 | Not recorded | 68fa7af71e209131cea86070 |
| CoE | 49 | Not recorded | 68fa7af71e209131cea86070 |
| Authority | 48 | Not recorded | 68fa7af71e209131cea86070 |
| HRAG | 48 | Not recorded | 68fa7af71e209131cea86070 |
| PRAG | 47 | Not recorded | 68fa7af71e209131cea86070 |
| HRAG | 47 | Not recorded | 68fa7af71e209131cea86070 |
| Authority | 47 | Not recorded | 68fa7af71e209131cea86070 |
| PRAG | 45 | Not recorded | 68fa7af71e209131cea86070 |
| PRAG | 41 | Not recorded | 68fa7af71e209131cea86070 |
| HRAG | 39 | Not recorded | 68fa7af71e209131cea86070 |
| HRAG | 39 | Not recorded | 68fa7af71e209131cea86070 |
| PRAG | 25 | Not recorded | 68fa7af71e209131cea86070 |
| HRAG | 25 | Not recorded | 68fa7af71e209131cea86070 |
| HRAG | 18 | Not recorded | 68fa7af71e209131cea86070 |

### AuthChain

ASR: 85. Result ID: 69d89cb047f34ce924c0dec5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Llama3-70B"}. This record does not assert independent reproduction.

### AuthChain

ASR: 84. Result ID: 69d89cb047f34ce924c0deb6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### AuthChain

ASR: 84. Result ID: 69d89cb047f34ce924c0debb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction.

### AuthChain

ASR: 83. Result ID: 69d89cb047f34ce924c0deca.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Deepseek-V3-0324"}. This record does not assert independent reproduction.

### AuthChain

ASR: 79. Result ID: 69d89cb047f34ce924c0dec0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction.

### AuthChain

ASR: 74. Result ID: 69d89cb047f34ce924c0deb1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

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

### Authority

ASR: 69. Result ID: 69d89cb047f34ce924c0dec4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Llama3-70B"}. This record does not assert independent reproduction.

### Authority

ASR: 67. Result ID: 69d89cb047f34ce924c0dec9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Deepseek-V3-0324"}. This record does not assert independent reproduction.

### Authority

ASR: 64. Result ID: 69d89cb047f34ce924c0debf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction.

### CoE

ASR: 62. Result ID: 69d89cb047f34ce924c0dec3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Llama3-70B"}. This record does not assert independent reproduction.

### CoE

ASR: 62. Result ID: 69d89cb047f34ce924c0dec8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Deepseek-V3-0324"}. This record does not assert independent reproduction.

### CoE

ASR: 61. Result ID: 69d89cb047f34ce924c0debe.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction.

### PRAG

ASR: 57. Result ID: 69d89cb047f34ce924c0dec6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa746c1e209131cea619c9.md>)

Recorded evaluation configuration: {"Model":"Deepseek-V3-0324"}. This record does not assert independent reproduction.

### CoE

ASR: 54. Result ID: 69d89cb047f34ce924c0deb9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction.

### PRAG

ASR: 54. Result ID: 69d89cb047f34ce924c0dec1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa746c1e209131cea619c9.md>)

Recorded evaluation configuration: {"Model":"Llama3-70B"}. This record does not assert independent reproduction.

### Authority

ASR: 53. Result ID: 69d89cb047f34ce924c0deb0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

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

### CoE

ASR: 52. Result ID: 69d89cb047f34ce924c0deaf.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

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

### CoE

ASR: 49. Result ID: 69d89cb047f34ce924c0deb4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### Authority

ASR: 48. Result ID: 69d89cb047f34ce924c0deb5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### HRAG

ASR: 48. Result ID: 69d89cb047f34ce924c0dec7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ef.md>)

Recorded evaluation configuration: {"Model":"Deepseek-V3-0324"}. This record does not assert independent reproduction.

### PRAG

ASR: 47. Result ID: 69d89cb047f34ce924c0dead.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa746c1e209131cea619c9.md>)

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

### HRAG

ASR: 47. Result ID: 69d89cb047f34ce924c0deb3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ef.md>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### Authority

ASR: 47. Result ID: 69d89cb047f34ce924c0deba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction.

### PRAG

ASR: 45. Result ID: 69d89cb047f34ce924c0debc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa746c1e209131cea619c9.md>)

Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction.

### PRAG

ASR: 41. Result ID: 69d89cb047f34ce924c0deb2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa746c1e209131cea619c9.md>)

Recorded evaluation configuration: {"Model":"GPT-4"}. This record does not assert independent reproduction.

### HRAG

ASR: 39. Result ID: 69d89cb047f34ce924c0deae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ef.md>)

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

### HRAG

ASR: 39. Result ID: 69d89cb047f34ce924c0debd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ef.md>)

Recorded evaluation configuration: {"Model":"Llama3-8B"}. This record does not assert independent reproduction.

### PRAG

ASR: 25. Result ID: 69d89cb047f34ce924c0deb7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa746c1e209131cea619c9.md>)

Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction.

### HRAG

ASR: 25. Result ID: 69d89cb047f34ce924c0deb8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ef.md>)

Recorded evaluation configuration: {"Model":"GPT-4o"}. This record does not assert independent reproduction.

### HRAG

ASR: 18. Result ID: 69d89cb047f34ce924c0dec2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7af71e209131cea86070.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75781e209131cea682ef.md>)

Recorded evaluation configuration: {"Model":"Llama3-70B"}. This record does not assert independent reproduction.

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