What is Claude Opus 4.5?

Claude Opus 4.5 is a large language model from Anthropic, released on November 24, 2025. It accepts text and image input.

When was Claude Opus 4.5 released?

Anthropic released Claude Opus 4.5 on November 24, 2025.

How much does Claude Opus 4.5 cost?

Claude Opus 4.5 costs $5 per 1M input tokens and $25 per 1M output tokens through the Anthropic API. Cached input costs $0.50 per 1M tokens. Prices are from Anthropic's official pricing as of October 5, 2026.

What is Claude Opus 4.5's context window?

Claude Opus 4.5 has a 200K-token context window and can generate up to 64K output tokens.

How does Claude Opus 4.5 score on benchmarks?

Claude Opus 4.5 has 39 cited benchmark scores, including Chess Puzzles (Epoch AI run) 12%, EBR-bench (Epoch AI run) 14.3% and FrontierMath Tier 4 v2 (Epoch AI run) 4.9%. Each score links to its source.

Claude Opus 4.5

Anthropic·Operational·Released 2025-11-24textvision

Context200k

Max output64k

Input / 1M$5 ↗

Output / 1M$25 ↗

Cached in$0.5

Benchmarks39

Benchmarks

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

Chess Puzzles (Epoch AI run)

#70/9212% ↗

EBR-bench (Epoch AI run)

#15/2414.3% ↗

FrontierMath Tier 4 v2 (Epoch AI run)

#51/574.9% ↗

FrontierMath Tiers 1-3 v2 (Epoch AI run)

#54/7334.4% ↗

Furniture Assembly (Epoch AI run)

#21/2928.3% ↗

GPQA Diamond (Epoch AI run)

#56/10286% ↗

LiveBench Agentic Coding (LiveBench)

#53/5639.7% ↗

LiveBench Coding (LiveBench)

#19/5679.7% ↗

LiveBench Data Analysis (LiveBench)

#30/5674.4% ↗

LiveBench Instruction Following (LiveBench)

#46/5662.5% ↗

LiveBench Language (LiveBench)

#24/5681.3% ↗

LiveBench Mathematics (LiveBench)

#29/5690.4% ↗

LiveBench Reasoning (LiveBench)

#42/5680.1% ↗

Mystery Game Puzzles (Epoch AI run)

#35/6822% ↗

OTIS Mock AIME 2024-2025 (Epoch AI run)

#62/10386.1% ↗

SAGE (Vals AI)

#8/7752.1% ↗

SimpleQA Verified (Epoch AI run)

#35/7145.7% ↗

SWE-bench Verified (Epoch AI run)

#8/3176.7% ↗

Vending-Bench 2 (Andon Labs)

#31/594967.06 ↗

WeirdML (Håvard Tveit Ihle)

#24/9263.7% ↗

LMArena Elo

#29/1411473.6 ↗

LMArena WebDev (LMArena)

#43/941493.3 ↗

tau2-bench Airline (Sierra)

#1/684% ↗

tau2-bench Banking Knowledge (Sierra)

#19/2224.7% ↗

tau2-bench Retail (Sierra)

#3/679.6% ↗

tau2-bench Telecom (Sierra)

#2/692.3% ↗

BALROG (BALROG)

#10/1943.5% ↗

GSO Opt@1 (GSO)

#12/2724.5% ↗

ARC-AGI-2 (Verified)

#7/837.6% ↗

GPQA Diamond

#33/8387% ↗

MCP Atlas

#8/1362.3% ↗

MMMLU

#3/990.8% ↗

MMMU (validation)

80.7% ↗

OSWorld

#2/866.3% ↗

SWE-bench Verified

#5/5980.9% ↗

Terminal-Bench 2.0

#7/2059.3% ↗

τ2-bench (Retail)

88.9% ↗

τ2-bench (Telecom)

98.2% ↗

SimpleBench (SimpleBench)

#27/7362% ↗

Compare

vs Gemini 4 Argon vs GPT-6.1 Sol vs Claude Sonnet 5.5 vs Muse Spark 1.3 vs GPT-6 Sol vs GPT-6 Luna vs Claude Opus 5.5 vs GPT-6 Astra

More from Anthropic

Claude Sonnet 5.5 Claude Opus 5.5 Claude Fable 5.1 Claude Opus 5 Claude Sonnet 5 Claude Haiku 4.5

Claude Opus 4.5 FAQ

What is Claude Opus 4.5?: Claude Opus 4.5 is a large language model from Anthropic, released on November 24, 2025. It accepts text and image input.
When was Claude Opus 4.5 released?: Anthropic released Claude Opus 4.5 on November 24, 2025.
How much does Claude Opus 4.5 cost?: Claude Opus 4.5 costs $5 per 1M input tokens and $25 per 1M output tokens through the Anthropic API. Cached input costs $0.50 per 1M tokens. Prices are from Anthropic's official pricing as of October 5, 2026.
What is Claude Opus 4.5's context window?: Claude Opus 4.5 has a 200K-token context window and can generate up to 64K output tokens.
How does Claude Opus 4.5 score on benchmarks?: Claude Opus 4.5 has 39 cited benchmark scores, including Chess Puzzles (Epoch AI run) 12%, EBR-bench (Epoch AI run) 14.3% and FrontierMath Tier 4 v2 (Epoch AI run) 4.9%. Each score links to its source.

Access Claude Opus 4.5 and every other model through one endpoint with automatic failover: Respan gateway.