# Deep Research on BrowseComp (Pass@1, Pass@3)

Source: [Deep Research on BrowseComp (Pass@1, Pass@3)](<https://www.sota2.com/research/sota/deep-research-on-browsecomp-pass-at-1-pass-at-3>)

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

Data updated: 2026-03-27T13:58:33.840Z

Evaluation of model performance on the Deep Research task using the BrowseComp dataset, measured by Pass@1 and Pass@3.

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 | Deep Research |
| Dataset (including any stated split) | BrowseComp |
| Metric | Pass@1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 33 of 33 |
| 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

- [Pass@1](<https://www.sota2.com/research/sota/deep-research-on-browsecomp-pass-at-1-pass-at-3.md?metric=Pass%401>): Higher is better; unit: PERCENT.

- [Pass@3](<https://www.sota2.com/research/sota/deep-research-on-browsecomp-pass-at-1-pass-at-3.md?metric=Pass%403>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pass@1 | Result date | Report paper |
| --- | --- | --- | --- |
| OpenAI-o3 | 50.9 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| DeepSeek-V3.1 | 30 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| WebSailor-30B | 19.5 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 18.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebExplorer-8B | 15.7 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| DeepDive-32B | 15.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 15 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-30B | 14.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| Kimi-K2 | 14.1 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| MiroThinker-32Bv0.1 | 13 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| Web-30B-E-GRPO | 12.9 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| WebSailor-30B | 12.8 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| Web-30B-GRPO | 12.3 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| WebSailor-7B | 12.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| Claude-4-Sonnet | 12.2 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| Web-30B-SFT | 10.8 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| WebSailor | 10.5 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| Web-7B-E-GRPO | 9.3 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| WebSailor-3B | 9.2 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| MiroThinker-8Bv0.1 | 8.7 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 8.5 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-7B | 8.5 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor | 6.7 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| Web-7B-GRPO | 6.3 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| WebSailor-7B | 5.8 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| Web-7B-SFT | 5.7 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| WebSailor-7B | 5.7 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| ASearcher-QWQ-32B | 5.2 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebSailor-3B | 4.2 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebDancer-QwQ | 3.8 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| WebSailor-3B | 3.3 | Not recorded | 68fa7c1e1e209131cea8c7b5 |
| WebThinker-RL | 2.8 | Not recorded | 69019f853ef7ccd74e5e3b78 |
| R1-Searcher | 0.4 | Not recorded | 69019f853ef7ccd74e5e3b78 |

### OpenAI-o3

Pass@1: 50.9. Result ID: 699ea3615698665ec46e40e5.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

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

### DeepSeek-V3.1

Pass@1: 30. Result ID: 699ea3615698665ec46e40e8.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

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

### WebSailor-30B

Pass@1: 19.5. Result ID: 69c68cf347f34ce924b0c4b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"MEM1-GRPO","Paradigm":"MEM1"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1: 18.3. Result ID: 69c68cf347f34ce924b0c4b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"ReSum-GRPO","Paradigm":"ReSum"}. This record does not assert independent reproduction.

### WebExplorer-8B

Pass@1: 15.7. Result ID: 69c68cf347f34ce924b0c4a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89abb.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### DeepDive-32B

Pass@1: 15.3. Result ID: 69c68cf347f34ce924b0c4a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c251e209131cea8caf8.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1: 15. Result ID: 69c68cf347f34ce924b0c4b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReSum"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1: 14.3. Result ID: 69c68cf347f34ce924b0c4b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### Kimi-K2

Pass@1: 14.1. Result ID: 699ea3615698665ec46e40e7.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

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

### MiroThinker-32Bv0.1

Pass@1: 13. Result ID: 69c68cf347f34ce924b0c4a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89abb.md>)

Recorded evaluation configuration: {"RL":"DPO","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### Web-30B-E-GRPO

Pass@1: 12.9. Result ID: 699ea3615698665ec46e40f3.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

Recorded evaluation configuration: {"Model Size":"30B","Training Strategy":"E-GRPO"}. This record does not assert independent reproduction.

### WebSailor-30B

Pass@1: 12.8. Result ID: 69c68cf347f34ce924b0c4b1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"-","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### Web-30B-GRPO

Pass@1: 12.3. Result ID: 699ea3615698665ec46e40f2.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

Recorded evaluation configuration: {"Model Size":"30B","Training Strategy":"GRPO"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1: 12.3. Result ID: 69c68cf347f34ce924b0c4b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"ReSum-GRPO","Paradigm":"ReSum"}. This record does not assert independent reproduction.

### Claude-4-Sonnet

Pass@1: 12.2. Result ID: 699ea3615698665ec46e40e6.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

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

### Web-30B-SFT

Pass@1: 10.8. Result ID: 699ea3615698665ec46e40f1.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

Recorded evaluation configuration: {"Model Size":"30B","Training Strategy":"SFT"}. This record does not assert independent reproduction.

### WebSailor

Pass@1: 10.5. Result ID: 699ea3615698665ec46e40ed.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79c91e209131cea7f5e0.md>)

Recorded evaluation configuration: {"Model Size":"32B"}. This record does not assert independent reproduction.

### Web-7B-E-GRPO

Pass@1: 9.3. Result ID: 699ea3615698665ec46e40f0.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

Recorded evaluation configuration: {"Model Size":"7B","Training Strategy":"E-GRPO"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1: 9.2. Result ID: 69c68cf347f34ce924b0c4ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"ReSum-GRPO","Paradigm":"ReSum"}. This record does not assert independent reproduction.

### MiroThinker-8Bv0.1

Pass@1: 8.7. Result ID: 69c68cf347f34ce924b0c4a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89abb.md>)

Recorded evaluation configuration: {"RL":"DPO","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1: 8.5. Result ID: 69c68cf347f34ce924b0c4ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReSum"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1: 8.5. Result ID: 69c68cf347f34ce924b0c4af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReSum"}. This record does not assert independent reproduction.

### WebSailor

Pass@1: 6.7. Result ID: 699ea3615698665ec46e40ec.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79c91e209131cea7f5e0.md>)

Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction.

### Web-7B-GRPO

Pass@1: 6.3. Result ID: 699ea3615698665ec46e40ef.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

Recorded evaluation configuration: {"Model Size":"7B","Training Strategy":"GRPO"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1: 5.8. Result ID: 69c68cf347f34ce924b0c4ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### Web-7B-SFT

Pass@1: 5.7. Result ID: 699ea3615698665ec46e40ee.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

Recorded evaluation configuration: {"Model Size":"7B","Training Strategy":"SFT"}. This record does not assert independent reproduction.

### WebSailor-7B

Pass@1: 5.7. Result ID: 69c68cf347f34ce924b0c4ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"-","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### ASearcher-QWQ-32B

Pass@1: 5.2. Result ID: 69c68cf347f34ce924b0c4a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba71e209131cea89abb.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1: 4.2. Result ID: 69c68cf347f34ce924b0c4aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"GRPO","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### WebDancer-QwQ

Pass@1: 3.8. Result ID: 699ea3615698665ec46e40eb.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8d1e209131cea83dce.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### WebSailor-3B

Pass@1: 3.3. Result ID: 69c68cf347f34ce924b0c4a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c1e1e209131cea8c7b5.md>)

Recorded evaluation configuration: {"RL":"-","Paradigm":"ReAct"}. This record does not assert independent reproduction.

### WebThinker-RL

Pass@1: 2.8. Result ID: 699ea3615698665ec46e40ea.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c191e209131cea8c4d7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### R1-Searcher

Pass@1: 0.4. Result ID: 699ea3615698665ec46e40e9.

[Reporting paper](<https://www.sota2.com/research/paper/69019f853ef7ccd74e5e3b78.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77771e209131cea7356d.md>)

Recorded evaluation configuration: {"Model Size":"7B"}. This record does not assert independent reproduction.

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