Models / Anthropic
Claude Sonnet 5.5
by Anthropic ·
anthropic/claude-sonnet-5.5Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...
reasoningtool-usevisionreleased 2026-09-28
Legal score · raw
-
not yet benchmarked
Context
1M
max output 128K
Input
$2.50
per 1M tokens
Output
$12.50
per 1M tokens
Suite cost
-
no run recorded
Prompt caching
Grounded answers re-send the same retrieved authority every turn, so a cached read is what a long matter actually costs. Prices are per 1M tokens, from the provider’s own catalog.
Cache read
$0.13
20x cheaper than uncached
Cache write
$3.13
per 1M tokens, charged once
Uncached input
$2.50
per 1M tokens
Capabilities
Modalities
in textimagefile
out text
Request parameters it accepts
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity
Benchmark results
This model has not been run through the suite yet. See Humanity's Last Lawsuit for the benchmark models are ranked on.
Measured by DocketBuster
These numbers come from DocketBuster's own legal battery, not from DocketRouter's suite. Latest run per metric, with n and a 95% Wilson interval where the source reports one. See docketbuster.com/benchmarks.
| Metric | Value | n | Interval | Measured |
|---|---|---|---|---|
| Statute pinpoint, exact section (no retrieval) | 11.3% (34/300) | 300 | 95% CI 8.2% to 15.4% | 2026-08-22 |
| Statute pinpoint, exact section (with DocketBuster retrieval) | 1.3% (4/307) | 307 | 95% CI 0.5% to 3.3% | 2026-08-25 |
| Say-nothing rate (declines to bluff when the answer is not in the record) | 100.0% | 144 | 95% CI 97.4% to 100.0% | 2026-08-22 |
| Abstained on statute pinpoint | 98.7% (303/307) | 307 | count, no interval reported | 2026-08-25 |
| Coaching quality (rubric, 0 to 8) | 7.28 / 8 | - | rubric mean, no interval reported | 2026-08-23 |