Claude Fable 5.2 lands 2nd on GDPx legal, behind Muse Wonder Full, up 4.6 points on Fable 5.1.
Fable 5.2 debuts at the top of the GDPx leaderboard scoring 16.4%. (1/7)🧵
4
3
24
1,441
Replying to @chakra_ai
Read more about the benchmark here:

gdpx.semianalysis.com/domains/legal
0
0
3
114
Chakra Labs’ mission is to maximize access to useful intelligence.

We're excited to partner with @SemiAnalysis_ on GDPx to measure how top models perform under realistic scenarios in legal domains.
Today we’re releasing GDPx, a benchmark for measuring agentic capabilities across the most valuable domains.

GDPx is a true frontier-level benchmark: even the best model scores just 12% (1/7)🧵
6
8
58
5,327
Replying to @chakra_ai
For GDPx, Chakra Labs contributed 20 legal tasks developed with senior-level attorneys across eight practice areas, from M&A and venture capital to intellectual property and dispute resolution.

The rubrics accept supported alternatives wherever reasonable lawyers could disagree. They give greater weight to the reasoning behind a conclusion rather than just the end outcome.

Importantly, weights scale with the consequences for the client, so missing the central legal issue costs more than a formatting error.
1
0
4
216
Chakra Labs retweeted
Fantastic day at @tryterac’s inaugural RL Summit - great mix of eng, research, and applied folks all in one room.

Thanks to @zacbakerr and @RyanMWexler for putting together such a sharp group, and for letting me share what we’re seeing at @chakra_ai. Excited to return next year!
4
7
31
1,280
Join us to accelerate the frontier
7
7
57
29,582
Update: Dojo now supports the OpenEnv spec.
20
25
125
25,910
Replying to @chakra_ai
Ex: access our Amazon clone using familiar Gymnasium style APIs.
7
7
44
6,346
Replying to @chakra_ai
To get started, check out our docs and code examples below. docs.trydojo.ai/integrations/o…
4
6
41
4,990
Chakra Labs retweeted
You can now run tasks in @chakra_ai's RL environments using Browserbase as the runtime.

Get task concurrency, isolated contexts, and enhanced observability.
Update: Dojo now supports @browserbase
19
12
81
10,110
Update: Dojo now supports @browserbase
8
13
74
15,840
Replying to @chakra_ai
We're excited to announce support for Browserbase, which allows researchers to quickly spin up 1000's of browser tasks concurrently using their serverless hosted infrastructure.

Researchers now benefit from:
- Hyper-scalable browser infra
- Secure SOC II instances
- Native on recordings
2
4
36
3,132
Replying to @chakra_ai
To get started with this custom run-time, check out the Dojo engine docs below:

docs.trydojo.ai/engines/browse…
2
2
24
2,589