Home Model series Claude Sonnet Claude Sonnet 5.5 Claude Sonnet 5.5 · FrontierSWE · v2 · Scores and configurations Claude Sonnet 5.5 · FrontierSWE · v2 · Scores and configurations Claude Sonnet 5.5 record for FrontierSWE · v2. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Sonnet 5.5 · FrontierSWE scores and configurations Metric and score Configuration and evaluation conditions Sources Mean score 61.9% Reported 61.9% · Unit % Published Unconfirmed
Max effort Settings Max reasoning effort. Unknowns Adaptive thinking status is benchmark-specific. Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol FrontierSWE v2, 34 ultra-long-horizon tasks; five trials per task. Conditions Proximal's own agent harness; max reasoning effort. View this score in rankings
Sources and disclosures §8.7, PDF p.114 Attachment · Claude Sonnet 5.5 System Card Benchmark versions and metrics Aliases FrontierSWE v2
Mean score · % · Higher is better