Claude Sonnet 4.6

Anthropic·Operational·Released 2026-02-17textvision

Context1,000k

Max output128k

Input / 1M$3 ↗

Output / 1M$15 ↗

Cached in$0.3

Benchmarks19

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

GPQA Diamond (Epoch AI run)

#38/7787.4% ↗

OTIS Mock AIME 2024-2025 (Epoch AI run)

#45/7685.8% ↗

SimpleQA Verified (Epoch AI run)

#32/5335.5% ↗

SWE-bench Verified (Epoch AI run)

#9/2475.2% ↗

LMArena Elo

#10/621458.3 ↗

ARC-AGI-2 (Verified)

#4/758.3% ↗

GDPval-AA

#1/21633 ↗

GPQA Diamond

#22/7089.9% ↗

Humanity's Last Exam (no tools)

#14/2933.2% ↗

Humanity's Last Exam (with tools)

#10/1349% ↗

MCP Atlas

#5/961.3% ↗

MMMLU

#3/489.3% ↗

MMMU-Pro (no tools)

#4/674.5% ↗

MMMU-Pro (with tools)

#6/775.6% ↗

OSWorld-Verified

#9/1272.5% ↗

SWE-bench Verified

#6/4579.6% ↗

Tau2-bench Retail

#2/391.7% ↗

Tau2-bench Telecom

#5/797.9% ↗

Terminal-Bench 2.0

#5/1359.1% ↗

Compare

vs GPT-6 Astra vs GPT-5.6 Sol vs GPT-5.6 Terra vs GPT-5.6 Luna vs Claude Fable 5.1 vs Claude Opus 5 vs Claude Sonnet 5 vs Claude Haiku 4.5

More from Anthropic

Claude Fable 5.1 Claude Opus 5 Claude Sonnet 5 Claude Haiku 4.5 Claude Opus 4.8 Claude Opus 4.7

Access Claude Sonnet 4.6 and every other model through one endpoint with automatic failover: Respan gateway.