Tabbit
Anthropic released Claude Sonnet 5.5 on September 28, 2026, with API model ID claude-sonnet-5-5. It targets well-scoped everyday tasks, bug fixes, and document creation. Availability in Tabbit depends on your account's live model picker.
Use in Tabbit Claude Sonnet 5.5
Claude Sonnet 5.5 · Model overview
A compact view of reviewed task guides, public evaluations, and evidence boundaries. Client access still depends on your current account.
Model access and permissions must be checked in the current Tabbit account.
Extract structured data, build a visual prototype, or start a coding task.
This official guide describes Sonnet 5.5-specific prompting patterns for effort, carrying work through, running without up-front thinking, structured JSON, progress updates, tool use, mid-turn user messages, and coding verification. You can use them to adjust .
Migrating to Claude Sonnet 5.5 means switching to claude-sonnet-5-5, adapting to adaptive thinking being enabled by default, removing non-default temperature, topp, and topk values and legacy assistant prefills, replacing forced tool use with auto plus strict .
Anthropic's current official configuration for Claude Sonnet 5.5 includes a 1M-token context window, a standard maximum output of 128K tokens, adaptive thinking with high as the default effort, $2 input pricing, and $10 output pricing; Bedrock is the only one .
This is a complete CLAUDE.md that can be added directly to a Claude Code project to guide Claude Sonnet 5.5 with scope control, dependency documentation lookups, real checks, and communication rules; the author explicitly says it is a personal configuration ba.
Public results use different versions, tiers, and harnesses; unknown values stay unknown.
Anthropic's launch page reports that Claude Sonnet 5.5 outperforms Sonnet 5 on selected agentic coding, knowledge work, computer use, and chart recognition benchmarks, with up to a 30% lower per-task cost through fewer task tokens. The page explicitly compares.
Artificial Analysis's independent evaluation places Claude Sonnet 5.5 at number 2 in the Artificial Analysis Intelligence Index with a score of 56 at max effort, and finds it close to Opus 5.5 on terminal Agent and knowledge work tasks, at the cost of the high.
In Arena.ai's published Code Arena: WebDev real-world evaluation, Claude Sonnet 5.5 (High) ranks fourth with a score of 1699 and enters the cost-efficiency Pareto frontier at a blended price of $8/Mtoken; it improves by 159 points over Sonnet 5 (High), but the.
Anthropic
Explore Claude Sonnet 5.5 specifications, prompts, and evaluation evidence, then check availability in Tabbit.