tinyfish web agent just scored 90% on mind2web bench
@Tiny_Fish13K followers
386,864 views
55 Comments
Comments from the original post on X (Twitter)

@Tiny_Fish
our open-source cookbook is trending 500+ stars in 5 days tonnes of use cases you can check out, try for free, and fork ⭐️ it:
64 likes

@Tiny_Fish
read more about our benchmark results: and here's the public spreadsheet of all the runs:
34 likes

@Saboo_Shubham_
great job you guys! the results look solid
8 likes

@Tiny_Fish
thank you, appreciate it
3 likes

@ai_for_success
The parallel execution is pretty amazing . Most web agents step through one action at a time and take a lot of time .
6 likes

@Tiny_Fish
yes exactly, this is how operations are done at scale
3 likes

@francedot
congrats for this release!!
5 likes

@Tiny_Fish
thanks a lot!
2 likes

@svpino
The benchmark numbers look solid! Congrats.
5 likes

@Tiny_Fish
Thank you so much!

@unwind_ai_
Covering in the next edition of
5 likes

@Polanco_IA
Structured outputs allow for immediate integration into pipelines. Congratulation 👏🏽
4 likes

@Tiny_Fish
exactly! nothing works in isolation
2 likes

@EyeingAI
transparency like this raises the bar for everyone👌
3 likes

@Tiny_Fish
Thanks how it should be done, thanks!

@not_simantak
A big congrats to the entire team!
3 likes

@Tiny_Fish
@Simantak242172 Thanks!

@Gargi__Gupta
300 tasks in 8 minutes 😳
3 likes

@Tiny_Fish
parallel execution 🙌
2 likes

@thetripathi58
TinyFish just raised the bar.
2 likes























