# CUA grounding on CUA grounding analytical projection OpenClaw

Source: [CUA grounding on CUA grounding analytical projection OpenClaw](<https://www.sota2.com/research/sota/cua-grounding-on-cua-grounding-analytical-projection-openclaw>)

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

Data updated: 2026-03-16T09:20:10.854Z

Evaluation of CUA grounding performance on the CUA grounding analytical projection OpenClaw dataset, measured using Esc. α, Eff. Acc., Cost/call, and Savings.

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 | CUA grounding |
| Dataset (including any stated split) | CUA grounding analytical projection OpenClaw |
| Metric | Esc. Alpha |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [Esc. Alpha](<https://www.sota2.com/research/sota/cua-grounding-on-cua-grounding-analytical-projection-openclaw.md?metric=Esc.%20Alpha>): Higher is better; unit: SCALAR.

- [Eff. Acc.](<https://www.sota2.com/research/sota/cua-grounding-on-cua-grounding-analytical-projection-openclaw.md?metric=Eff.%20Acc.>): Higher is better; unit: PERCENT.

- [Cost/Call ($)](<https://www.sota2.com/research/sota/cua-grounding-on-cua-grounding-analytical-projection-openclaw.md?metric=Cost%2FCall%20(%24)>): Lower is better; unit: SCALAR.

- [Savings](<https://www.sota2.com/research/sota/cua-grounding-on-cua-grounding-analytical-projection-openclaw.md?metric=Savings>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Esc. Alpha | Result date | Report paper |
| --- | --- | --- | --- |
| All on 72B | 1 | Not recorded | 69b78e6c0636e5bf4afbdaeb |
| Cold AVR | 0.35 | Not recorded | 69b78e6c0636e5bf4afbdaeb |
| Warm AVR | 0.15 | Not recorded | 69b78e6c0636e5bf4afbdaeb |
| Warm AVR + difficulty | 0.1 | Not recorded | 69b78e6c0636e5bf4afbdaeb |

### All on 72B

Esc. Alpha: 1. Result ID: 69b7cb2e47f34ce9249fb93d.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e6c0636e5bf4afbdaeb.md>)

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

Recorded evaluation configuration: {"Scenario":"All on 72B","Model pool":"7B/72B"}. This record does not assert independent reproduction.

### Cold AVR

Esc. Alpha: 0.35. Result ID: 69b7cb2e47f34ce9249fb93e.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e6c0636e5bf4afbdaeb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e6c0636e5bf4afbdaeb.md>)

Recorded evaluation configuration: {"Scenario":"Cold AVR","Model pool":"7B/72B"}. This record does not assert independent reproduction.

### Warm AVR

Esc. Alpha: 0.15. Result ID: 69b7cb2e47f34ce9249fb93f.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e6c0636e5bf4afbdaeb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e6c0636e5bf4afbdaeb.md>)

Recorded evaluation configuration: {"Scenario":"Warm AVR","Model pool":"7B/72B"}. This record does not assert independent reproduction.

### Warm AVR + difficulty

Esc. Alpha: 0.1. Result ID: 69b7cb2e47f34ce9249fb940.

[Reporting paper](<https://www.sota2.com/research/paper/69b78e6c0636e5bf4afbdaeb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b78e6c0636e5bf4afbdaeb.md>)

Recorded evaluation configuration: {"Scenario":"Warm AVR + difficulty","Model pool":"7B/72B"}. This record does not assert independent reproduction.

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