Skip to main content
MANIFOLD
Top OSWorld 2.0 score by end of 2026
2
Ṁ1kṀ582
Dec 31
76%
chance

OSWorld 2.0 is a long-horizon benchmark for computer use with median human time per task of 1.6 hours

https://osworld-v2.xlang.ai/

What top binary reward score will be achieved by the end of 2026? Will consider the official leaderboard and other credible sources (to my best judgement).

OSWorld 2.0: Benchmarking computer-use agents on long-horizon real-world tasks
OSWorld 2.0: Benchmarking computer-use agents on long-horizon real-world tasks
Market context
AI
Technology
Technical AI Timelines
AI Impacts
AI Benchmarks
Get
Ṁ1,000
to start trading!
Sort by:
bought Ṁ300 YES

For context GPT-5.6 Sol is 62.6%

People are also trading

What will be the best GSOBench score by Dec 31, 2026?
What will be the best score (almost resolved) on ProgramBench at the end of 2026?
Best score on CritPt benchmark (~FrontierMath for physics) by end of 2026
63.7
Will a non-Windows, non-Unix-like operating system capture greater than 3% market share by 2043?
50% chance
Will the social network 2 release by the end of 2027?
96% chance
What will be the highest Epoch Capabilities Index score in 2026?
Will a non-Windows, non-Unix-like operating system capture greater than 3% market share by 2033?
31% chance
Will Safari remain the 2nd most popular browser by the end of 2026?
62% chance
Top score on Humanity's Last Exam > 50% by 2029?
99% chance
Microsoft ships a Linux desktop by 2032?
16% chance