Browser agent benchmarks

Our extraction benchmark task, 10 runs, 2 runtimes, 5 models. A careers page listing 14 vacancies whose listings live inside an embedded job board on another domain, so a naive read of the page returns nothing at all. Every run had the same schema, the same spending cap, and had to come back with all 14.

What it cost69% less
OpenBrowse$0.24
Browser Use Cloud$0.78
Tokens burned76% less
OpenBrowse202k
Browser Use Cloud859k
Time to finish31% faster
OpenBrowse1m 47s
Browser Use Cloud2m 36s
Sort by
RuntimeModelReasoningStepsTimeTokensLLM costRecords
OpenBrowsegpt-5.6-lunamax3617m 03s1.08M$0.2214/14
OpenBrowsegpt-5.6-terranone111m 47s202k$0.2414/14
OpenBrowseclaude-sonnet-5high104m 02s242k$0.4014/14
OpenBrowsegpt-5.6-solnone82m 03s136k$0.4114/14
OpenBrowseclaude-sonnet-5none95m 18s237k$0.5114/14
OpenBrowsegpt-5.6-terrahigh175m 05s434k$0.6614/14
Browser Use Cloudclaude-sonnet-5high102m 36s859k$0.7814/14invented fields
OpenBrowsegpt-5.6-solmedium165m 24s339k$1.1214/14
OpenBrowseclaude-opus-5medium153m 56s398k$1.3214/14
OpenBrowseclaude-opus-5none174m 53s480k$1.6214/14

Showing 10 of 10 runs.

Every OpenBrowse run recovered all 14 records without inventing a field. Browser Use Cloud recovered all 14 too, and populated values the page never displayed, job seniority among them.

Costs are LLM token spend. OpenBrowse charges nothing on top, and Browser Use Cloud's own platform fee is not in its figure, so the real difference in what you pay is wider than this.

What we learned running it

The saving is token efficiency, not a cheaper model
Hold the model steady and the gap is still there. claude-sonnet-5 at reasoning high costs $0.78 on Browser Use Cloud and $0.40 here, because the run burns 242k tokens instead of 859k. What changes is how many tokens the runtime spends getting the agent to the answer.
Reading a whole listing at once is where it goes
Open 14 pages one at a time and you pay for 14 rounds of page context. read_pages resolves the same 14 in three waves of real tabs, so the agent reasons over the set instead of rebuilding context per page.
We do not recommend our own cheapest run
gpt-5.6-luna at reasoning max was the cheapest complete extraction at $0.22, and it took 17m 03s to get there. gpt-5.6-terra at none cost two cents more and finished in 1m 47s. That is why the cheapest row is not the recommended one.
Every reasoning level got the same answer
Every OpenBrowse run recovered 14 of 14 records at every reasoning level. What moved was time, steps and cost, sometimes threefold. Treat reasoningEffort as a cost and latency control and set it deliberately per model family.

Reasoning cuts both ways

On browser tasks the two families fail in opposite directions. OpenAI models do better with less reasoning: they spend less time planning ahead and more time reacting to the page actually in front of them. Anthropic's 5-series Claude models lean towards rabbit holes and need reasoning time to refocus on the goal.

OpenAI

Turn it down

gpt-5.6-terra costs $0.24 at reasoning none and $0.66 at high. At high it also burns 2.15x the tokens, takes 17 steps instead of 11 and runs 3m 18s longer.

Anthropic

Turn it up

claude-sonnet-5 costs $0.40 at reasoning high and $0.51 at none. At none it also runs 1m 16s longer.

More reasoning is not simply better, and the right answer moves in opposite directions depending on who made the model. This is why a session that sends no reasoningEffort runs at the level measured here rather than at whatever the provider would have chosen unprompted.

Which model to reach for

Three starting points, depending on what you are optimising for.

For most use cases
  • gpt-5.6-terranone
  • gpt-5.6-solnone
  • claude-sonnet-5high

The best balance of reliability, accuracy and cost.

For intense workflows
  • claude-opus-5medium
  • gpt-5.6-solnone

Both are strong here, but watch token burn.

On a budget
  • gpt-5.6-lunamax

Pair it with a tightly focused prompt. It takes a while and it is more prone to hallucination on broad prompts, but the extractions themselves are still good quality.

OpenAI

supported
  • gpt-5.6-sol
  • gpt-5.6-terra
  • gpt-5.6-luna

Anthropic

supported
  • claude-mythos-5
  • claude-fable-5
  • claude-opus-5
  • claude-sonnet-5
  • claude-opus-4.8
  • claude-opus-4.8[1m]
  • claude-opus-4.7
  • claude-opus-4.7[1m]
  • claude-opus-4.6
  • claude-opus-4.6[1m]
  • claude-sonnet-4.6
  • claude-sonnet-4.6[1m]

Google

coming soon

Not available yet.

Run it yourself

OpenBrowse runs on any Debian or Ubuntu machine, from a Raspberry Pi to a VPS, and installs in about ten minutes. Point an existing browser-use-sdk client at it, send it the same task file these runs used, and compare what comes back against the rows above.