Models/Claude 4.1 Opus

MDL

Claude 4.1 Opus

Anthropic

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$15 / $75

in / out

Context

—

Avg score

59.5

10 benchmarks

AA Intelligence

33.7

index

Speed

39 tok/s

TTFT 9.7s

Released

Aug 5, 2025

About

Claude 4.1 Opus is a proprietary model in the Claude family from Anthropic. Benchmarked on 10 evals, averaging 59.5.

Benchmark scores · 10

avg 59.5 — higher is better

MMLU-Proartificial-analysis · 2026-07

GPQA Diamondartificial-analysis · 2026-07

80.9

AIMEartificial-analysis · 2026-07

80.3

τ²-benchartificial-analysis · 2026-07

71.4

AA Long-Context Reasoningartificial-analysis · 2026-07

66.3

LiveCodeBenchartificial-analysis · 2026-07

65.4

IFBenchartificial-analysis · 2026-07

55.4

SciCodeartificial-analysis · 2026-07

40.9

Terminal-Bench Hardartificial-analysis · 2026-07

34.3

Humanity's Last Examartificial-analysis · 2026-07

11.9

Details

PublisherAnthropic

FamilyClaude

Parameters—

License—

WeightsClosed

ReleasedAug 5, 2025

Performance & price

Output speed39 tok/s

Latency (TTFT)9.7s

Price in / out$15 / $75 per 1M

Blended price$30 / 1M

Math index80.3

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

History

full ledger →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers

Artificial Analysis$75/M