Model
Model explorer

Claude Sonnet 4.6

CLOSED
Anthropic · Claude 4 family · released Feb 17, 2026

CONFIRMED REAL — this is not a mix-up. Model id claude-sonnet-4-6. Direct predecessor to Claude Sonnet 5, sitting between Sonnet 4.5 and Sonnet 5 in the lineage; the corpus is missing it even though it already has both Opus 4.6 (2026-02-05) and Sonnet 5 (2026-06-30). Introduced 1M-token context (beta) and adaptive thinking for the Sonnet line.

ReasoningCodingVisionFunction callingTool useAgentic
2417.2
Elo · rank #42
Parameters
Undisclosed
Active params
—
Context
1M tokens
Architecture
Dense transformer, architecture undisclosed
License
Proprietary
Languages
—
API price (in/out)
$3 / $15
Modalities
text · vision
Benchmark results
Bar shows position within the tracked field; marker = field best
Agents' Last ExamAgents32.0%#15
best: GPT-6 Astra · 59.3%
AIMEMath95.6%#12
best: GPT-5.2 · 100.0%
ARC-AGI-2Reasoning58.3%#13
best: GPT-6 Astra · 95.0%
BrowseCompAgents74.0%#24
best: Kimi K3 · 91.2%
CharXivVision72.4%#28
best: Qwen3.8-Flash-Next · 90.6%
GDPval-AAAgents1633#11
best: Claude Fable 5 · 1932
GPQA DiamondReasoning89.9%#34
best: GPT-6 Astra · 96.0%
Humanity's Last ExamReasoning49.0%#11
best: Claude Opus 5 · 64.7%
LiveCodeBenchCoding82.1%#41
best: DeepSeek-V4-Pro (Think Max) · 93.5%
MMLU-ProKnowledge87.3%#10
best: Claude Fable 5 · 91.5%
MMMLUKnowledge89.3%#9
best: Gemini 3.1 Pro · 92.6%
MMMU-ProVision83.6%#3
best: Claude Opus 4.7 · 85.5%
OSWorld-VerifiedAgents72.5%#16
best: Claude Fable 5 · 85.0%
SWE-bench ProCoding58.1%#23
best: Claude Fable 5.1 · 81.2%
SWE-bench VerifiedCoding79.6%#21
best: Claude Opus 5 · 96.0%
τ²-Bench RetailAgents91.7%#1
best: this model · 91.7%
τ²-Bench TelecomAgents97.9%#10
best: Claude Opus 4.6 · 99.3%
Terminal-Bench 2.0Coding67.0%#32
best: Gemini 3.8 Flash · 89.4%
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
$3
Output / M tok
$15
Claude 4 family
Elo progression across releases
Claude Opus 4May 20251674.4Claude Sonnet 4May 20251566.9Claude Opus 4.1Aug 20251733.8Claude Sonnet 4.5Sep 20251938.8Claude Haiku 4.5Oct 20251556.0Claude Opus 4.5Nov 20252228.2Claude Opus 4.5 (High)Nov 20252261.5Claude Opus 4.5 (Medium)Nov 20252255.6Claude Opus 4.6Feb 20262433.7Claude Sonnet 4.6Feb 20262417.2Claude Opus 4.7Apr 20262674.5Claude Opus 4.8May 20262756.0
Resources
DOCShttps://platform.claude.com/docs/en/about-claude/models/overviewAPIAvailable via Anthropic API
API price $3/$15 · each benchmark row carries its own source badge (see methodology)