Claude Opus 4.7

Anthropic·Operational·Released 2026-04-16textvision

Context1,000k

Max output128k

Input / 1M$5 ↗

Output / 1M$25 ↗

Cached in$0.5

Benchmarks18

Benchmarks

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

AIME 2026 (MathArena)

#12/2195.8% ↗

FrontierMath Tier 4 v2 (Epoch AI run)

#16/4431.7% ↗

FrontierMath Tiers 1-3 v2 (Epoch AI run)

#16/5970.2% ↗

GPQA Diamond (Epoch AI run)

#27/7790.2% ↗

OTIS Mock AIME 2024-2025 (Epoch AI run)

#11/7697.8% ↗

SimpleQA Verified (Epoch AI run)

#13/5351.7% ↗

SWE-bench Verified (Epoch AI run)

#1/2483.5% ↗

LMArena Elo

#2/621483.4 ↗

BrowseComp

#8/1579.8% ↗

GPQA Diamond

#6/7094.2% ↗

Humanity's Last Exam (no tools)

#4/2946.9% ↗

Humanity's Last Exam (with tools)

#7/1354.7% ↗

OSWorld-Verified

#4/1282.8% ↗

SWE-bench Multilingual

#3/780.5% ↗

SWE-bench Multimodal

#2/234.5% ↗

SWE-Bench Pro

#4/1564.3% ↗

SWE-bench Verified

#2/4587.6% ↗

Terminal-Bench 2.1

#14/1766.1% ↗

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 4.6

Access Claude Opus 4.7 and every other model through one endpoint with automatic failover: Respan gateway.