When will SWE-bench be solved?
Basic
4
Ṁ20
2030
8%
2024
30%
2025
18%
2026
8%
2027
8%
2028
8%
2029
19%
later

Resolves to the first year in which https://www.swebench.com posts a 90% resolved score in the “verified” category. The current score is 38.80% by Amazon Q Developer Agent.

Get
Ṁ1,000
and
S3.00
Sort by:
bought Ṁ5 later YES

Relatively significant chance of never (which resolves at later). Frontier LLMs are just going to get more and more contaminated with this benchmark's test data - at some point authors might just stop tracking

© Manifold Markets, Inc.Terms + Mana-only TermsPrivacyRules