Home Model series Claude Sonnet Claude Sonnet · SWE-bench Multilingual · 300 problems, 9 programming languages · Release history Claude Sonnet · SWE-bench Multilingual · 300 problems, 9 programming languages · Release history View scores, configurations, and disclosures for SWE-bench Multilingual · 300 problems, 9 programming languages across 3 Claude Sonnet releases, ordered by release date.
Differences are calculated only for unique, active, exact values between direct predecessors when the unit, metric, and explicitly recorded configuration and conditions match.
2026-02-17 · 1 score record for this release, including 1 exact value (may include historical records)
Claude Sonnet 4.6 · SWE-bench Multilingual scores and configurations Metric and score Configuration and evaluation conditions Sources Pass rate 75.9% Reported 75.9% · Unit % Published Unconfirmed
Adaptive thinking, max effort Settings Adaptive thinking enabled; max effort; default temperature and top_p unless an evaluation specifies otherwise. Unknowns Context window is evaluation-dependent; Table 2.1.A states it does not exceed 1M tokens. Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol 300 problems across 9 programming languages; 10 trials. Conditions Adaptive thinking, max effort, default sampling; thinking blocks included in sampling results. View this score in rankings
§2.2, PDF p.16 Attachment · Claude Sonnet 4.6 System Card 2026-06-30 · 1 score record for this release, including 1 exact value (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
Claude Sonnet 5 · SWE-bench Multilingual scores and configurations Metric and score Configuration and evaluation conditions Sources Pass rate 78.3% Reported 78.3% · Unit % Published Unconfirmed
Standard configuration: adaptive thinking, max effort Settings Adaptive thinking at max effort; default temperature and top_p; five-trial averages unless otherwise stated. Unknowns Context-window size is evaluation-dependent; standard configuration is 1M tokens. Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol 300 problems across 9 programming languages; five trials. Conditions Standard configuration; thinking blocks included in sampling results. View this score in rankings
§8.2, PDF p.116 Attachment · Claude Sonnet 5 System Card 2026-09-28 · 1 score record for this release, including 1 exact value (may include historical records)
Records for the direct predecessor do not provide matching conditions for a valid difference.
Claude Sonnet 5.5 · SWE-bench Multilingual scores and configurations Metric and score Configuration and evaluation conditions Sources Pass rate 90.3% Reported 90.3% · Unit % Published Unconfirmed
Adaptive thinking, max effort Settings Adaptive thinking enabled; max effort. Unknowns Sampling settings may vary by benchmark; see each result.conditions. Tools Tool access not recorded Reasoning budget max Framework not recorded Protocol SWE-Bench Multilingual, 300 problems across 9 programming languages; five-trial average. Conditions No further harness details stated in this section. View this score in rankings
§8.2, PDF p.110 Attachment · Claude Sonnet 5.5 System Card