Development

Anthropic models improving ~2% per month on SWE-bench Verified

development2025-12-11

Claim

Anthropic's models are reported improving about 2% per month on SWE-bench Verified, on track to saturate it by late 2026.

Reporting date: 2025-12-11 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to December 11, 2025 (theinnermostloop.substack.com)

A rate, not a score — the newsletter’s habit of tracking slopes and projected saturation dates rather than leaderboard positions.

Knowledge graphopen in browser →

About

SWE-bench Verified

Reported in

Welcome to December 11, 2025

Actor

Anthropic

Referenced by

Cite or correct this record

Citation formatCitation text

Anthropic models improving ~2% per month on SWE-bench Verified
Innermost Loop KB — secondary record
Reporting date: 2025-12-11
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2025-12-11-anthropic-swebench-trajectory
Claim: Anthropic's models are reported improving about 2% per month on SWE-bench Verified, on track to saturate it by late 2026.
Attributed sources:
- Welcome to December 11, 2025 — https://theinnermostloop.substack.com/p/welcome-to-december-11-2025
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.