evals.report
BenchmarksLabsCompareRun guidesIn the wild
AnthropicClaude Sonnet

Claude Sonnet 5.5

Anthropic · Claude Sonnet. Released Sep 28, 2026.

Claude Sonnet 5.5 is a model from Anthropic in the Claude Sonnet family, released Sep 28, 2026. evals.report tracks 8 reported Claude Sonnet 5.5 benchmark scores across ARC-AGI-2, ARC-AGI-1, FrontierCode, FrontierCode 2.0, AA-Omniscience v1.1: Knowledge and Hallucination Benchmark, AA-Omniscience: Knowledge and Hallucination Benchmark, Humanity's Last Exam, SWE-bench Pro — each shown with its benchmark, metric, source status, and date, and never combined into a single ranking.

8 results

Benchmark results 8

Compare this model
BenchmarkCategoryScoreMetricStatusDate
ARC-AGI-2Reasoning83.89%accuracyOfficialSep 28, 2026Details
ARC-AGI-1Reasoning96.5%accuracyOfficialSep 28, 2026Details
FrontierCodeCoding52.1%weighted score (Main)OfficialSep 28, 2026Details
FrontierCode 2.0Coding42.2%weighted score (Main)OfficialSep 28, 2026Details
AA-Omniscience v1.1: Knowledge and Hallucination BenchmarkReasoning30AA-Omniscience Net ScoreOfficialSep 28, 2026Details
AA-Omniscience: Knowledge and Hallucination BenchmarkReasoning32AA-Omniscience IndexOfficialSep 28, 2026Details
Humanity's Last ExamReasoning56.9%accuracyVerifiedSep 28, 2026Details
SWE-bench ProCoding81.3%% resolvedUnverifiedSep 28, 2026Details