← Back to model catalog

VENICE ATLAS · MODEL DOSSIER · CLAUDE SONNET 5.5

Model overview

Claude Sonnet 5.5

Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.

claude-sonnet-5-5 · venice.ai
Text · Venice catalog$2.00 per 1M tokensPrice on Venice AI
ModalityTextOn Venice AI
Primary price$2.00 per 1M tokensper 1M tokens
Context window1MMax tokens
Benchmarks47Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Agents6 results
AA-Briefcase v1.1aa-briefcase-1.1 · agents
60.4%
ReportedOct 2026
AutomationBenchautomationbench · agents
44.7%
ReportedOct 2026
OfficeQAofficeqa · agents
76.9%
ReportedOct 2026
OfficeQA Proofficeqa-pro · agents
65.6%
ReportedOct 2026
Program Benchprogram-bench · agents
79.7%
ReportedOct 2026
Toolathlon-Verifiedtoolathlon-verified · agents
77.8%
ReportedOct 2026
Biology11 results
Biomedical image analysisbiomedical-image-analysis · biology
72.2%
ReportedOct 2026
BioMysteryBenchbiomysterybench · biology
89.2%
ReportedOct 2026
BioMysteryBench (Human Difficult)biomysterybench-difficult · biology
44.7%
ReportedOct 2026
De novo protein binder designde-novo-protein-binder-design · biology
82.3%
ReportedOct 2026
LatchBio SpatialBench Verifiedlatchbio-spatialbench-verified · biology
72.5%
ReportedOct 2026
Medicinal Chemistry (ADME)medicinal-chemistry-adme · biology
65.3%
ReportedOct 2026
Morphology-to-molecule matchingmorphology-to-molecule-matching · biology
25.0%
ReportedOct 2026
Protein Design — Library Rankingprotein-design-library-ranking · biology
54.8%
ReportedOct 2026
Protein Design — Sequence Generationprotein-design-sequence-generation · biology
51.0%
ReportedOct 2026
Protocols Troubleshootingprotocols-troubleshooting · biology
67.3%
ReportedOct 2026
Protocols Understanding (V2)protocols-understanding-v2 · biology
66.6%
ReportedOct 2026
Coding5 results
BenchCADbenchcad · code
74.7%
ReportedOct 2026
BenchCAD (with Python tool)benchcad-with-python-tool · code
96.3%
ReportedOct 2026
CursorBench 4.0cursorbench-4.0 · code
55.5%
ReportedOct 2026
DeepSWE 1.1deepswe-1.1 · code
71.0%
ReportedOct 2026
FrontierSWE V2frontierswe-v2 · code
61.9%
ReportedOct 2026
General intelligence2 results
GDPval-AA 2.1gdpval-aa-2.1 · general
61.5%
ReportedOct 2026
Global-MMLUglobal-mmlu · general
92.1%
ReportedOct 2026
Healthcare5 results
HealthBenchhealthbench · healthcare
65.4%
ReportedOct 2026
HealthBench (raw)healthbench-raw · healthcare
69.4%
ReportedOct 2026
HealthBench Professionalhealthbench-professional · healthcare
69.2%
ReportedOct 2026
HealthBench Professional (raw)healthbench-professional-raw · healthcare
77.1%
ReportedOct 2026
PhysicianBenchphysicianbench · healthcare
63.2%
ReportedOct 2026
Language1 result
MILUmilu · language
91.6%
ReportedOct 2026

Learn what each benchmark measures ↗

Related models

More from anthropic