Claude Sonnet 3.5 v2

Balanced Claude model for coding, analysis, agent workflows, and cost control

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

RELEASE DATEOct 22, 2024
WEIGHTSClosed weights
CONTEXT WINDOW200K
MAX OUTPUT8.2K
REASONINGNo
TOOL CALLINGYes
INPUTStext, image, pdf
OUTPUTStext

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.