vibecodingnav
中/EN
Models/claude-sonnet-4-6

Claude Sonnet 4.6

27th on DeepSWE v1.1 Best (high) at 29.9%.

Anthropic · Proprietary · Fetched 2026-10-10

DeepSWE v1.1
29.9%
#27 / 28 · 25.8–34.0

Benchmark scores

Boards older than 90 days are not counted as recommendations
BenchmarkSettingScoreRankCostAs of
DeepSWE v1.1high · mini-swe-agent29.925.8–34.0#27$5.522026-09-22
SWE-bench Verified—This board has stopped updating——2026-02-26
Aider Polyglot—This board has stopped updating——2025-11-20

Use it or not

Why
  • Still has a checkable historical-tier score on DeepSWE.
When not
  • Well behind Sonnet 5 / 5.5; do not merge the rows.

Appears in these scenarios

Collected from scenario boards
Build a Web frontend#27DeepSWE 29.9%Build an Android app#27DeepSWE 29.9%Write CLI, scripts, and DevOps#27DeepSWE 29.9%

Peers