# Built with it

Published articles for Built with it.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Jev's WebMCP benchmark results and agent performance claims

DevFeed: [Jev's WebMCP benchmark results and agent performance claims](<https://devfeed.tech/articles/jev-drops-the-waitlist-theo-trashes-instant-compaction-55862.md>)

Original publisher: [Read original article](<https://jevdaily.com/issues/2026-09-21-w7>)

Author: Jev Weekly

Published: 2026-09-21T17:00:00Z

Content type: news

Language: en

Sources: [Jev Daily](<https://devfeed.tech/sources/jev-daily.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [client](<https://devfeed.tech/topics/client.md>), [computer-use](<https://devfeed.tech/topics/computer-use.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Search engine optimization (SEO)](<https://devfeed.tech/topics/seo.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [built-with-it](<https://devfeed.tech/tags/built-with-it.md>), [code](<https://devfeed.tech/tags/code.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [evals](<https://devfeed.tech/tags/evals.md>), [execution](<https://devfeed.tech/tags/execution.md>), [latency](<https://devfeed.tech/tags/latency.md>), [seo](<https://devfeed.tech/tags/seo.md>), [someone-measured-it](<https://devfeed.tech/tags/someone-measured-it.md>), [the-case-against](<https://devfeed.tech/tags/the-case-against.md>), [webmcp](<https://devfeed.tech/tags/webmcp.md>), [writing-criteria](<https://devfeed.tech/tags/writing-criteria.md>)

### AI overview

A weekly roundup reports benchmark and integration results for Jev, including 49 of 49 WebMCP tasks solved with Mercury 2.5 and lower reported model costs than GPT-6 Astra. It also describes claimed improvements in browser-agent latency, task success, SEO audit costs, and database evaluation.

### Source excerpt

idan levin's WebMCP benchmark went from 25 of 49 tasks to 49 of 49 once he handed Jev website tools instead of raw page controls. That is the week in one...

## Jev aced one browser benchmark, scored 1/20 on another

DevFeed: [Jev aced one browser benchmark, scored 1/20 on another](<https://devfeed.tech/articles/jev-aced-one-browser-benchmark-scored-1-20-on-another-55860.md>)

Original publisher: [Read original article](<https://jevdaily.com/issues/2026-09-19-w7>)

Author: Jev Weekly

Published: 2026-09-19T17:00:00Z

Content type: news

Language: en

Sources: [Jev Daily](<https://devfeed.tech/sources/jev-daily.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [browser](<https://devfeed.tech/topics/browser.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [computer-use](<https://devfeed.tech/topics/computer-use.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Latency](<https://devfeed.tech/topics/latency.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [also-on-the-timeline](<https://devfeed.tech/tags/also-on-the-timeline.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [browser](<https://devfeed.tech/tags/browser.md>), [built-with-it](<https://devfeed.tech/tags/built-with-it.md>), [computer-use](<https://devfeed.tech/tags/computer-use.md>), [evals](<https://devfeed.tech/tags/evals.md>), [latency](<https://devfeed.tech/tags/latency.md>), [llm](<https://devfeed.tech/tags/llm.md>), [someone-measured-it](<https://devfeed.tech/tags/someone-measured-it.md>), [the-case-against](<https://devfeed.tech/tags/the-case-against.md>), [writing-criteria](<https://devfeed.tech/tags/writing-criteria.md>)

### AI overview

A roundup of Jev results across browser agents, computer-use benchmarks, latency tests, cost comparisons, classification pipelines, and long-horizon tasks. Reported results range from major gains on some benchmarks to a 1/20 score on another, alongside concerns about cost and context compaction.

### Source excerpt

Gregor Zunic shipped a Jev browser agent that found flights in 7 seconds for $0.0039, then benchmarked the same approach at 1 of 20 on long horizon tasks...