Home Model series Claude Sonnet Claude Sonnet · Multi-task Indic Language Understanding Benchmark · 10 Indic languages plus English · overall average · Release history Claude Sonnet · Multi-task Indic Language Understanding Benchmark · 10 Indic languages plus English · overall average · Release history View scores, configurations, and disclosures for Multi-task Indic Language Understanding Benchmark · 10 Indic languages plus English · overall average 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 · Multi-task Indic Language Understanding Benchmark scores and configurations Metric and score Configuration and evaluation conditions Sources Average accuracy 89.6% Reported 89.6% · 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 Provider defaults; structured JSON output; successfully parsed responses only. Conditions 11 种语言整体均值,含英语;Adaptive thinking;Max effort。 View this score in rankings
§2.19.2 Table 2.19.2.A, PDF p.43 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 · Multi-task Indic Language Understanding Benchmark scores and configurations Metric and score Configuration and evaluation conditions Sources Average accuracy 89.3% Reported 89.3% · 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 MILU average accuracy; five-trial average. Conditions Adaptive thinking at max effort. View this score in rankings
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 · Multi-task Indic Language Understanding Benchmark scores and configurations Metric and score Configuration and evaluation conditions Sources Average accuracy 91.6% Reported 91.6% · 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 Tools forbidden Reasoning budget max Framework not recorded Protocol MILU average accuracy across 10 Indic languages plus English; five-trial average. Conditions Adaptive thinking and max effort; no tools or customized system prompt. View this score in rankings
§8.16.2 Figure 8.16.2.A, PDF p.140 Attachment · Claude Sonnet 5.5 System Card PDF p.140, Section 8.16.2 and Figure 8.16.2.A Attachment · Claude Sonnet 5.5 System Card