# Web Navigation and Skill Induction on Mind2Web Cross-Website GPT-4.1

Source: [Web Navigation and Skill Induction on Mind2Web Cross-Website GPT-4.1](<https://www.sota2.com/research/sota/web-navigation-and-skill-induction-on-mind2web-cross-website-gpt-4-1>)

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

Data updated: 2026-06-17T07:18:49.830Z

Evaluation of agent performance on the Mind2Web Cross-Website GPT-4.1 dataset, focusing on Web Navigation and Skill Induction capabilities, reporting Success Rate (SR), average LLM action count, and library size.

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 | Web Navigation / Skill Induction |
| Dataset (including any stated split) | Mind2Web Cross-Website GPT-4.1 |
| Metric | Success Rate (SR) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Success Rate (SR)](<https://www.sota2.com/research/sota/web-navigation-and-skill-induction-on-mind2web-cross-website-gpt-4-1.md?metric=Success%20Rate%20(SR)>): Higher is better; unit: PERCENT.

- [Average LLM Action Count](<https://www.sota2.com/research/sota/web-navigation-and-skill-induction-on-mind2web-cross-website-gpt-4-1.md?metric=Average%20LLM%20Action%20Count>): Lower is better; unit: SCALAR.

- [Library Size (\|K\|)](<https://www.sota2.com/research/sota/web-navigation-and-skill-induction-on-mind2web-cross-website-gpt-4-1.md?metric=Library%20Size%20(%7CK%7C)>): Lower is better; unit: SIZE.

## Recorded results

| Method | Success Rate (SR) | Result date | Report paper |
| --- | --- | --- | --- |
| PolySkill | 61.3 | Not recorded | 6a322a00d33dfb23e783ea55 |
| SKILLMIGRATOR | 60.5 | Not recorded | 6a322a00d33dfb23e783ea55 |
| ASI | 58.7 | Not recorded | 6a322a00d33dfb23e783ea55 |
| PolySkill | 57.6 | Not recorded | 6a322a00d33dfb23e783ea55 |
| SKILLMIGRATOR | 57.1 | Not recorded | 6a322a00d33dfb23e783ea55 |
| ReAct | 56.2 | Not recorded | 6a322a00d33dfb23e783ea55 |
| ASI | 54.9 | Not recorded | 6a322a00d33dfb23e783ea55 |

### PolySkill

Success Rate (SR): 61.3. Result ID: 6a324a42fbc373592c2f6435.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

Recorded evaluation configuration: {"Library Regime":"+Update","Base LLM":"GPT-4.1"}. This record does not assert independent reproduction.

### SKILLMIGRATOR

Success Rate (SR): 60.5. Result ID: 6a324a42fbc373592c2f6436.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

Recorded evaluation configuration: {"Library Regime":"+Update","Base LLM":"GPT-4.1"}. This record does not assert independent reproduction.

### ASI

Success Rate (SR): 58.7. Result ID: 6a324a42fbc373592c2f6434.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aee1e209131cea85d66.md>)

Recorded evaluation configuration: {"Library Regime":"+Update","Base LLM":"GPT-4.1"}. This record does not assert independent reproduction.

### PolySkill

Success Rate (SR): 57.6. Result ID: 6a324a42fbc373592c2f6432.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

Recorded evaluation configuration: {"Library Regime":"Static","Base LLM":"GPT-4.1"}. This record does not assert independent reproduction.

### SKILLMIGRATOR

Success Rate (SR): 57.1. Result ID: 6a324a42fbc373592c2f6433.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

Recorded evaluation configuration: {"Library Regime":"Static","Base LLM":"GPT-4.1"}. This record does not assert independent reproduction.

### ReAct

Success Rate (SR): 56.2. Result ID: 6a324a42fbc373592c2f6430.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6eb41e209131cea41992.md>)

[Implementation](<https://react-lm.github.io/>)

Recorded evaluation configuration: {"Library Regime":"Static","Base LLM":"GPT-4.1"}. This record does not assert independent reproduction.

### ASI

Success Rate (SR): 54.9. Result ID: 6a324a42fbc373592c2f6431.

[Reporting paper](<https://www.sota2.com/research/paper/6a322a00d33dfb23e783ea55.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aee1e209131cea85d66.md>)

Recorded evaluation configuration: {"Library Regime":"Static","Base LLM":"GPT-4.1"}. This record does not assert independent reproduction.

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