# Enterprise interface interaction on WorkArena L2 full benchmark

Source: [Enterprise interface interaction on WorkArena L2 full benchmark](<https://www.sota2.com/research/sota/enterprise-interface-interaction-on-workarena-l2-full-benchmark>)

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

Data updated: 2026-04-10T08:05:12.795Z

Evaluation of agent performance on the full WorkArena L2 benchmark suite, focusing on the ability to complete enterprise interface interaction tasks, measured by 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 | Enterprise interface interaction |
| Dataset (including any stated split) | WorkArena L2 full benchmark |
| Metric | Success Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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/enterprise-interface-interaction-on-workarena-l2-full-benchmark.md?metric=Success%20Rate>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Success Rate | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-5 | 69.4 | Not recorded | 69d883f37d0172140ec77912 |
| Claude 4 Sonnet | 40.4 | Not recorded | 69d883f37d0172140ec77912 |
| GPT-oss-120B | 11.5 | Not recorded | 69d883f37d0172140ec77912 |

### GPT-5

Success Rate: 69.4. Result ID: 69d8af1c47f34ce924c15e82.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f37d0172140ec77912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77261e209131cea7167a.md>)

Recorded evaluation configuration: {"Harness":"GenericAgent","Params":"-"}. This record does not assert independent reproduction.

### Claude 4 Sonnet

Success Rate: 40.4. Result ID: 69d8af1c47f34ce924c15e83.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f37d0172140ec77912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77261e209131cea7167a.md>)

Recorded evaluation configuration: {"Harness":"GenericAgent","Params":"-"}. This record does not assert independent reproduction.

### GPT-oss-120B

Success Rate: 11.5. Result ID: 69d8af1c47f34ce924c15e84.

[Reporting paper](<https://www.sota2.com/research/paper/69d883f37d0172140ec77912.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77261e209131cea7167a.md>)

Recorded evaluation configuration: {"Harness":"GenericAgent","Params":"120B"}. This record does not assert independent reproduction.

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