Benchmarks / WorkArena
WorkArena
Built by ServiceNow · Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam H. Laradji, et al. · released 12 Mar 2024
Browser tasks on a live ServiceNow enterprise instance, the software many companies use for IT and HR requests. WorkArena-L1 has 33 task types (19,912 instances) that cover the main parts of the ServiceNow interface: forms, lists, knowledge base search, service catalog orders, and dashboards.
Frontier
90.3%
WorkArena-L1 success rate
IpaziaHPA-Gemini-3-flash-preview · harness: IpaziaHPA · agent: IpaziaHPA (Ipazia S.p.a.)
7 Mar 2026 · Source: Ipazia S.p.a. (submitted to the ServiceNow BrowserGym leaderboard) (third party)
Top WorkArena-L1 entry on the leaderboard as of 2026-09-23. Standard error 1.6. Uses the accessibility tree, no screenshots. Max steps raised from 15 to 30, so the file marks it as not following the standard protocol. Self-submitted; not re-run by ServiceNow.
The best result is at 90% or more of the ceiling.
What it measures
Whether a web agent completes routine enterprise-software actions from a text instruction. Each task samples a fresh configuration, and a checker validates the result in the ServiceNow instance. WorkArena++ (L2 and L3, 682 tasks) composes these atomic actions into longer workflows that need planning and reasoning, but the public leaderboard currently lists results only for L1.
WorkArena-L1 success rate: Share of sampled WorkArena-L1 task instances completed, as reported on the BrowserGym leaderboard with standard error. Higher is better.
Status compares the frontier with a ceiling of 100%.
Facts
- Grain
- Task level: bounded tasks with a clear spec
- Environment
- browser, live-system
- Grading
- state-check
- Tasks
- 33
- Contamination
- Task templates are public, but each run samples new instances. The maintainers have not published a contamination analysis.
- Reuse
- Apache 2.0 for the benchmark code. Running tasks needs access to a ServiceNow developer instance. (open-apache)
Limits to keep in mind
- Leaderboard entries are self-submitted result files. The top entry raised the step budget from 15 to 30 and is marked as not following the standard evaluation protocol. Source
- L1 tasks are short atomic actions. The harder WorkArena++ (L2, L3) tasks have no entries on the public leaderboard, so the board understates how far agents are from full workflows. Source
- Few agents have been submitted (about 20 folders), and several have no WorkArena result at all. Source
- All tasks run on one vendor's platform, so results say little about other enterprise software. Source
Recorded results
A selection that shows the frontier over time. The full leaderboard is at the source.
| System | WorkArena-L1 success rate | Date | Source |
|---|---|---|---|
| IpaziaHPA-Gemini-3-flash-preview · frontier harness: IpaziaHPA | 90.3% | 7 Mar 2026 | Ipazia S.p.a. (submitted to the ServiceNow BrowserGym leaderboard) · third-party |
| GenericAgent-Claude-4-Sonnet harness: BrowserGym GenericAgent | 63.3% | 7 Aug 2025 | ServiceNow · primary |
| GenericAgent-GPT-5 harness: BrowserGym GenericAgent | 79.1% | 7 Aug 2025 | ServiceNow · primary |
| GenericAgent-GPT-4o harness: BrowserGym GenericAgent | 45.5% | 23 Oct 2024 | ServiceNow · primary |
Timeline
- 12 Mar 2024 — ServiceNow Research releases WorkArena and BrowserGym. Source
Where it sits in the atlas
Office and administrative supportDevOps, SRE, and IT operations (partial)
Go to the source
- Website github.com
- Paper arxiv.org
- Full leaderboard huggingface.co
- Code github.com
Last checked 23 Sep 2026 against 6 primary sources. See an error? Tell us.
How to cite
Credit the original work first: WorkArena by ServiceNow (https://arxiv.org/abs/2403.07718).
Then, if you used this page:
Can Agents Work. "WorkArena: frontier results and sources." https://canagentswork.com/benchmarks/workarena/ (accessed 2026-09-24). CC BY 4.0.@misc{caw-workarena,
title = {{WorkArena: frontier results and sources}},
author = {{Can Agents Work}},
year = {2026},
howpublished = {\url{https://canagentswork.com/benchmarks/workarena/}},
note = {Accessed 2026-09-24. CC BY 4.0}
}