# Room Navigation on Room Navigation Common Sense - CS

Source: [Room Navigation on Room Navigation Common Sense - CS](<https://www.sota2.com/research/sota/room-navigation-on-room-navigation-common-sense-cs>)

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

Data updated: 2026-06-04T10:52:01.801Z

Evaluation of agent performance for Room Navigation within the Room Navigation Common Sense - CS environment, measured by metrics like Success 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 | Room Navigation |
| Dataset (including any stated split) | Room Navigation Common Sense - CS |
| Metric | Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 29 of 29 |
| 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](<https://www.sota2.com/research/sota/room-navigation-on-room-navigation-common-sense-cs.md?metric=Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| SceneDiver | 65.3 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Thinking | 63.3 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SoM | 62.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Base Model | 62 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Multi-Res | 60.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SceneDiver | 53.3 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SceneDiver | 52.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SceneDiver | 48 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Multi-Res | 46.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| VCD | 46 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SoM | 44.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Base Model | 43.3 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Multi-Res | 41.3 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Thinking | 41.3 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Base Model | 40 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SoM | 40 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Multi-Res | 38.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SoM | 38 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Base Model | 37.3 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SceneDiver | 36 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Multi-Res | 32.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SceneDiver | 32.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| VCD | 32 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SoM | 31.3 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Base Model | 30.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| VCD | 24.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| SoM | 24 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Base Model | 22.7 | Not recorded | 6a2106ddc10484bac23f04f3 |
| Multi-Res | 20.7 | Not recorded | 6a2106ddc10484bac23f04f3 |

### SceneDiver

Success Rate: 65.3. Result ID: 6a2158c2fbc373592c1ddbed.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"gemini-2.5-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### Thinking

Success Rate: 63.3. Result ID: 6a2158c2fbc373592c1ddbec.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: {"Backbone":"gemini-2.5-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### SoM

Success Rate: 62.7. Result ID: 6a2158c2fbc373592c1ddbea.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71221e209131cea4f649.md>)

Recorded evaluation configuration: {"Backbone":"gemini-2.5-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### Base Model

Success Rate: 62. Result ID: 6a2158c2fbc373592c1ddbe9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"gemini-2.5-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### Multi-Res

Success Rate: 60.7. Result ID: 6a2158c2fbc373592c1ddbeb.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62ebc.md>)

[Implementation](<https://github.com/Yuliang-Liu/Monkey>)

Recorded evaluation configuration: {"Backbone":"gemini-2.5-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### SceneDiver

Success Rate: 53.3. Result ID: 6a2158c2fbc373592c1ddbe8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"gpt-4o-mini","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### SceneDiver

Success Rate: 52.7. Result ID: 6a2158c2fbc373592c1ddbdf.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-32B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### SceneDiver

Success Rate: 48. Result ID: 6a2158c2fbc373592c1ddbf2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"doubao-seed-1.6-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### Multi-Res

Success Rate: 46.7. Result ID: 6a2158c2fbc373592c1ddbdd.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62ebc.md>)

[Implementation](<https://github.com/Yuliang-Liu/Monkey>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-32B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### VCD

Success Rate: 46. Result ID: 6a2158c2fbc373592c1ddbde.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-32B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### SoM

Success Rate: 44.7. Result ID: 6a2158c2fbc373592c1ddbdc.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71221e209131cea4f649.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-32B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### Base Model

Success Rate: 43.3. Result ID: 6a2158c2fbc373592c1ddbdb.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-32B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### Multi-Res

Success Rate: 41.3. Result ID: 6a2158c2fbc373592c1ddbf0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62ebc.md>)

[Implementation](<https://github.com/Yuliang-Liu/Monkey>)

Recorded evaluation configuration: {"Backbone":"doubao-seed-1.6-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### Thinking

Success Rate: 41.3. Result ID: 6a2158c2fbc373592c1ddbf1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c311e209131cea8cef5.md>)

Recorded evaluation configuration: {"Backbone":"doubao-seed-1.6-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### Base Model

Success Rate: 40. Result ID: 6a2158c2fbc373592c1ddbee.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"doubao-seed-1.6-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### SoM

Success Rate: 40. Result ID: 6a2158c2fbc373592c1ddbef.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71221e209131cea4f649.md>)

Recorded evaluation configuration: {"Backbone":"doubao-seed-1.6-flash","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### Multi-Res

Success Rate: 38.7. Result ID: 6a2158c2fbc373592c1ddbe7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62ebc.md>)

[Implementation](<https://github.com/Yuliang-Liu/Monkey>)

Recorded evaluation configuration: {"Backbone":"gpt-4o-mini","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### SoM

Success Rate: 38. Result ID: 6a2158c2fbc373592c1ddbe6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71221e209131cea4f649.md>)

Recorded evaluation configuration: {"Backbone":"gpt-4o-mini","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### Base Model

Success Rate: 37.3. Result ID: 6a2158c2fbc373592c1ddbe5.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"gpt-4o-mini","Model Category":"Closed-Source"}. This record does not assert independent reproduction.

### SceneDiver

Success Rate: 36. Result ID: 6a2158c2fbc373592c1ddbda.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### Multi-Res

Success Rate: 32.7. Result ID: 6a2158c2fbc373592c1ddbd8.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62ebc.md>)

[Implementation](<https://github.com/Yuliang-Liu/Monkey>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### SceneDiver

Success Rate: 32.7. Result ID: 6a2158c2fbc373592c1ddbe4.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### VCD

Success Rate: 32. Result ID: 6a2158c2fbc373592c1ddbd9.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053d.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### SoM

Success Rate: 31.3. Result ID: 6a2158c2fbc373592c1ddbd7.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71221e209131cea4f649.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### Base Model

Success Rate: 30.7. Result ID: 6a2158c2fbc373592c1ddbd6.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"Qwen2.5-VL-7B-Instruct-AWQ","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### VCD

Success Rate: 24.7. Result ID: 6a2158c2fbc373592c1ddbe3.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71461e209131cea5053d.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### SoM

Success Rate: 24. Result ID: 6a2158c2fbc373592c1ddbe1.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71221e209131cea4f649.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### Base Model

Success Rate: 22.7. Result ID: 6a2158c2fbc373592c1ddbe0.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B","Model Category":"Open-Source"}. This record does not assert independent reproduction.

### Multi-Res

Success Rate: 20.7. Result ID: 6a2158c2fbc373592c1ddbe2.

[Reporting paper](<https://www.sota2.com/research/paper/6a2106ddc10484bac23f04f3.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74a51e209131cea62ebc.md>)

[Implementation](<https://github.com/Yuliang-Liu/Monkey>)

Recorded evaluation configuration: {"Backbone":"InternVL2.5-8B","Model Category":"Open-Source"}. This record does not assert independent reproduction.

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