Skip to main content
MANIFOLD
Will DeepSWE be ≥90% solved at <$5/task before 2027?
3
Ṁ1kṀ1.2k
Dec 31
41%
chance

This market resolves YES if, before Jan 1, 2027, 00:00 UTC, any model listed on the official Datacurve DeepSWE leaderboard reaches both:

  1. ≥90% Pass@1, and

  2. average cost per task <$5.00.

Use the displayed point estimates on the official leaderboard only.

Market context
Technology
AI
Business
Technical AI Timelines
AI Impacts
Get
Ṁ1,000
to start trading!
Sort by:

Same question at any cost: /adssx/will-deepswe-be-saturated-before-20

People are also trading

When will SWE-bench be solved?
Will an AI achieve >85% performance on the FrontierMath benchmark before 2027?
39% chance
In what year will AI achieve a score of 95% or higher on the SWE-bench Verified benchmark?
12/10/26
AI resolves at least X% on SWE-bench without any assistance, by 2028?
Will an AI achieve >80% performance on the FrontierMath benchmark before 2027?
67% chance
AI resolves at least X% on SWE-bench WITH assistance, by 2028?
Will any of DeepMind's formal conjectures be resolved before 2027?
99% chance
Will AI solve 100% of solvable MTurk problems by July 2028?
32% chance
Will DeepSWE be saturated before 2027 (≥90%)?
+36% 1d86% chance
Will an autonomous agent resolve 90% of tasks on SWE-bench by 2027?
85% chance