Claude 2.1

Anthropic

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

26.8

6 benchmarks

AA Intelligence

3.9

index

Weights

Closed

Released

Nov 21, 2023

About

Claude 2.1 is a proprietary model in the Claude family from Anthropic. Benchmarked on 6 evals, averaging 26.8.

Benchmark scores · 6

avg 26.8 — higher is better

MMLU-Proartificial-analysis · 2026-07

49.5

MATHartificial-analysis · 2026-07

37.4

GPQA Diamondartificial-analysis · 2026-07

31.9

LiveCodeBenchartificial-analysis · 2026-07

19.5

SciCodeartificial-analysis · 2026-07

18.4

Humanity's Last Examartificial-analysis · 2026-07

4.2

Details

PublisherAnthropic

FamilyClaude

Parameters—

License—

WeightsClosed

ReleasedNov 21, 2023

Performance & price

Price in / out$0 / $0 per 1M

Coding index14.0

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$0/M