# Inquire-driven GUI Navigation on InquireBench Chinese

Source: [Inquire-driven GUI Navigation on InquireBench Chinese](<https://www.sota2.com/research/sota/inquire-driven-gui-navigation-on-inquirebench-chinese>)

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

Data updated: 2026-04-28T06:50:03.405Z

Evaluation of agent performance on the InquireBench Chinese dataset for Inquire-driven GUI Navigation, reporting metrics including ISR, SR, and Score.

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 | Inquire-driven GUI Navigation |
| Dataset (including any stated split) | InquireBench Chinese |
| Metric | SR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [SR](<https://www.sota2.com/research/sota/inquire-driven-gui-navigation-on-inquirebench-chinese.md?metric=SR>): Higher is better; unit: PERCENT.

- [ISR](<https://www.sota2.com/research/sota/inquire-driven-gui-navigation-on-inquirebench-chinese.md?metric=ISR>): Higher is better; unit: PERCENT.

- [Score](<https://www.sota2.com/research/sota/inquire-driven-gui-navigation-on-inquirebench-chinese.md?metric=Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | SR | Result date | Report paper |
| --- | --- | --- | --- |
| InquireMobile | 10.5 | Not recorded | 68fa7ae11e209131cea85a28 |
| GUI-R1-3B | 9.5 | Not recorded | 68fa7ae11e209131cea85a28 |
| Claude-3.5-Sonnet v2 | 8.4 | Not recorded | 68fa7ae11e209131cea85a28 |
| Qwen2.5-VL-72B | 6.7 | Not recorded | 68fa7ae11e209131cea85a28 |
| UI-R1-3B | 5.3 | Not recorded | 68fa7ae11e209131cea85a28 |
| GUI-Owl | 5.3 | Not recorded | 68fa7ae11e209131cea85a28 |
| InquireMobile | 5.3 | Not recorded | 68fa7ae11e209131cea85a28 |
| Gemini-2.5-pro | 4.2 | Not recorded | 68fa7ae11e209131cea85a28 |
| UI-R1-3B-E | 4.2 | Not recorded | 68fa7ae11e209131cea85a28 |
| Qwen2.5-VL-3B | 4.2 | Not recorded | 68fa7ae11e209131cea85a28 |
| Claude-3.5-Sonnet v2 | 3.2 | Not recorded | 68fa7ae11e209131cea85a28 |
| InquireMobile | 3.2 | Not recorded | 68fa7ae11e209131cea85a28 |
| GPT-4o-0806 | 2.1 | Not recorded | 68fa7ae11e209131cea85a28 |
| GPT-4o-0806 | 2.1 | Not recorded | 68fa7ae11e209131cea85a28 |
| Gemini-2.5-pro | 1 | Not recorded | 68fa7ae11e209131cea85a28 |
| Qwen2.5-VL-72B | 1 | Not recorded | 68fa7ae11e209131cea85a28 |

### InquireMobile

SR: 10.5. Result ID: 69f0579b47f34ce924d592b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"Model-based Framework","Backbone":"Qwen2.5-VL-3B","Training Stage":"Stage1 & Stage2"}. This record does not assert independent reproduction.

### GUI-R1-3B

SR: 9.5. Result ID: 69f0579b47f34ce924d592ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bbf1e209131cea8a2a0.md>)

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

### Claude-3.5-Sonnet v2

SR: 8.4. Result ID: 69f0579b47f34ce924d592a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"AppAgent Framework"}. This record does not assert independent reproduction.

### Qwen2.5-VL-72B

SR: 6.7. Result ID: 69f0579b47f34ce924d592a1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"AppAgent Framework"}. This record does not assert independent reproduction.

### UI-R1-3B

SR: 5.3. Result ID: 69f0579b47f34ce924d592a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c61e209131cea7a6e2.md>)

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

### GUI-Owl

SR: 5.3. Result ID: 69f0579b47f34ce924d592ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b111e209131cea867fb.md>)

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

### InquireMobile

SR: 5.3. Result ID: 69f0579b47f34ce924d592af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"Model-based Framework","Backbone":"Qwen2.5-VL-3B","Training Stage":"Stage2"}. This record does not assert independent reproduction.

### Gemini-2.5-pro

SR: 4.2. Result ID: 69f0579b47f34ce924d592a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"Mobile-Agent-E Framework"}. This record does not assert independent reproduction.

### UI-R1-3B-E

SR: 4.2. Result ID: 69f0579b47f34ce924d592aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c61e209131cea7a6e2.md>)

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

### Qwen2.5-VL-3B

SR: 4.2. Result ID: 69f0579b47f34ce924d592ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa773a1e209131cea71d3c.md>)

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

### Claude-3.5-Sonnet v2

SR: 3.2. Result ID: 69f0579b47f34ce924d592a8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"Mobile-Agent-E Framework"}. This record does not assert independent reproduction.

### InquireMobile

SR: 3.2. Result ID: 69f0579b47f34ce924d592ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"Model-based Framework","Backbone":"Qwen2.5-VL-3B","Training Stage":"Stage1"}. This record does not assert independent reproduction.

### GPT-4o-0806

SR: 2.1. Result ID: 69f0579b47f34ce924d592a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"AppAgent Framework"}. This record does not assert independent reproduction.

### GPT-4o-0806

SR: 2.1. Result ID: 69f0579b47f34ce924d592a6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"Mobile-Agent-E Framework"}. This record does not assert independent reproduction.

### Gemini-2.5-pro

SR: 1. Result ID: 69f0579b47f34ce924d592a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"AppAgent Framework"}. This record does not assert independent reproduction.

### Qwen2.5-VL-72B

SR: 1. Result ID: 69f0579b47f34ce924d592a5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ae11e209131cea85a28.md>)

Recorded evaluation configuration: {"Framework":"Mobile-Agent-E Framework"}. This record does not assert independent reproduction.

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