Models / Anthropic

Claude Sonnet 5

by Anthropic · anthropic/claude-sonnet-5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

reasoningtool-usevisionreleased 2026-06-30

JSON Route to this model

Legal score · raw

not yet benchmarked

Context

max output 128K

Input

per 1M tokens

Output

$10

per 1M tokens

Suite cost

run the suite to see

Benchmark results

Task	Category	Raw	Juiced	Correct	Latency	Cost	Ran
Hearsay Identification	Evidence	-	-	-	-	-	-
Bluebook Citation Format	Research & Writing	-	-	-	-	-	-
Federal Civil Procedure	Procedure	-	-	-	-	-	-
Limitations Arithmetic	Procedure	-	-	-	-	-	-
Contract Clause Classification	Contracts	-	-	-	-	-	-
Citation Hallucination Resistance	Reliability	-	-	-	-	-	-

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 (GW-14x, 0 to 8)	7.28 / 8	-	rubric mean, no interval reported	2026-08-23

Source files: hard-llm-ortier-sonnet5.json, gw14x-ortier-sonnet5.json, hard-llm-level-sonnet5-statute_rag.json. Raw model name in source: anthropic/claude-sonnet-5.