# CAPTCHA Solving on geetest/gobang CAPTCHA zero-shot

Source: [CAPTCHA Solving on geetest/gobang CAPTCHA zero-shot](<https://www.sota2.com/research/sota/captcha-solving-on-geetest-gobang-captcha-zero-shot>)

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

Data updated: 2026-03-26T15:00:31.976Z

Evaluation of CAPTCHA Solving performance on the geetest/gobang CAPTCHA zero-shot dataset, measured by solve rate.

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 | CAPTCHA Solving |
| Dataset (including any stated split) | geetest/gobang CAPTCHA zero-shot |
| Metric | Solve Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Solve Rate](<https://www.sota2.com/research/sota/captcha-solving-on-geetest-gobang-captcha-zero-shot.md?metric=Solve%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Solve Rate | Result date | Report paper |
| --- | --- | --- | --- |
| Halligan | 36 | Not recorded | 69c4bd640636e5bf4afc742f |
| ReCAP-32B | 3 | Not recorded | 69c4bd640636e5bf4afc742f |
| Qwen-32B | 2 | Not recorded | 69c4bd640636e5bf4afc742f |
| ReCAP-8B | 0 | Not recorded | 69c4bd640636e5bf4afc742f |
| Qwen-8B | 0 | Not recorded | 69c4bd640636e5bf4afc742f |

### Halligan

Solve Rate: 36. Result ID: 69c54a0747f34ce924af6433.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc742f.md>)

Recorded evaluation configuration: {"Zero-shot evaluation protocol":"true","Training status":"task-specific framework"}. This record does not assert independent reproduction.

### ReCAP-32B

Solve Rate: 3. Result ID: 69c54a0747f34ce924af6432.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc742f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc742f.md>)

Recorded evaluation configuration: {"Zero-shot evaluation protocol":"true","Model parameter scale":"32B","Training status":"finetuned"}. This record does not assert independent reproduction.

### Qwen-32B

Solve Rate: 2. Result ID: 69c54a0747f34ce924af6435.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc742f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Zero-shot evaluation protocol":"true","Model parameter scale":"32B","Training status":"base"}. This record does not assert independent reproduction.

### ReCAP-8B

Solve Rate: 0. Result ID: 69c54a0747f34ce924af6431.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc742f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc742f.md>)

Recorded evaluation configuration: {"Zero-shot evaluation protocol":"true","Model parameter scale":"8B","Training status":"finetuned"}. This record does not assert independent reproduction.

### Qwen-8B

Solve Rate: 0. Result ID: 69c54a0747f34ce924af6434.

[Reporting paper](<https://www.sota2.com/research/paper/69c4bd640636e5bf4afc742f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Zero-shot evaluation protocol":"true","Model parameter scale":"8B","Training status":"base"}. This record does not assert independent reproduction.

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