Model
Model explorer

Claude Sonnet 5

CLOSED
Anthropic · Claude 5 family · released Jun 30, 2026

Model id claude-sonnet-5. Drop-in upgrade for Sonnet 4.6: adaptive thinking on by default, manual extended-thinking removed (400 error), new tokenizer (~30% more tokens for same text vs Sonnet 4.6), non-default sampling params rejected. Introductory pricing $2/$10 per MTok through 2026-08-31, standard pricing $3/$15 thereafter (used here). On Terminal-Bench 2.1 and GDPval-AA v2 it narrowly beats Opus 4.8 despite Sonnet-tier pricing. NO SEPARATE '(High)' PRODUCT: Anthropic's docs state explicitly that setting effort to 'high' 'produces exactly the same behavior as omitting the effort parameter entirely,' and high is the documented default — there is no distinct marketed 'Sonnet 5 (High)' SKU to add as a sibling entry. Pricing correction (Oct 2026): Sonnet 5 launched at $2/$10 per MTok and Anthropic made that the standard price on Aug 10, 2026, cancelling the planned Sep 1 increase to $3/$15, so $3/$15 was never charged.

ReasoningCodingVisionFunction callingTool useAgentic
2353.3
Elo · rank #57
Parameters
Undisclosed
Active params
—
Context
1M tokens
Architecture
Dense transformer, architecture undisclosed; adaptive thinking on by default, controlled by a runtime effort parameter (low/medium/high/xhigh/max)
License
Proprietary
Languages
—
API price (in/out)
$2 / $10
Modalities
text · vision
Benchmark results
Bar shows position within the tracked field; marker = field best
AIMEMath86.7%#60
best: GPT-5.2 · 100.0%
Arena EloHuman preference1461#32
best: Claude Fable 5 · 1504
BrowseCompAgents84.7%#9
best: Kimi K3 · 91.2%
CharXivVision77.0%#26
best: Qwen3.8-Flash-Next · 90.6%
CursorBench 4.0Coding34.1%#7
best: Claude Opus 5.5 · 57.8%
FrontierBenchAgents14.6%#7
best: Claude Opus 5 · 43.3%
GDPval-AAAgents1618#12
best: Claude Fable 5 · 1932
GPQA DiamondReasoning90.5%#28
best: GPT-6 Astra · 96.0%
Humanity's Last ExamReasoning57.4%#6
best: Claude Opus 5.5 · 67.7%
LiveCodeBenchCoding82.4%#40
best: DeepSeek-V4-Pro (Think Max) · 93.5%
OSWorld-VerifiedAgents81.2%#6
best: Claude Fable 5 · 85.0%
SWE-bench ProCoding63.2%#12
best: Claude Opus 5.5 · 89.9%
SWE-bench VerifiedCoding79.6%#28
best: Claude Opus 5 · 97.0%
Terminal-Bench 2.0Coding80.4%#21
best: DeepSeek-V4.1-Flash · 90.6%
API price $2/$10 · each benchmark row carries its own source badge (see methodology)