Compare

DeepSeek R2 vs Claude Opus 4.7

DeepSeek vs Anthropic. Specs, benchmarks, and real per-task cost — all in one page.

Verdict

DeepSeek R2 is ~31.3× cheaper on a 3:1 input:output blend. DeepSeek R2 is open-weights, the other is proprietary.

DeepSeek

DeepSeek’s reasoning variant. Competes with o4 on math at a fraction of the cost.

Frontier math at open-weights pricingLong CoT traces

Anthropic

Anthropic’s frontier reasoning model. Leads SWE-Bench and holds top ranks on long-context coding and agentic workflows.

Best-in-class coding agent behaviorStrong instruction following1M-token context with high recallHigh reliability under tool use

Pricing

Input / 1M$0.55$15.00

Output / 1M$2.19$75.00

Context128K1.0M

Max output64K64K

LicenseOpen weightsProprietary

Released2026-01-152026-03-12

Benchmarks

LMSYS ELO—1412.0

MMLU Pro87.892.8

HumanEval90.194.4

SWE-Bench—72.1

MATH94.189.3

GPQA71.266.4

MMMU—79.2

IFEval—92.1

Per-task cost

Summarize a 1-hour meeting transcript$0.0093$0.263

Review a 500-line pull request$0.0088$0.270

Answer a customer support ticket$0.0034$0.105

Extract structured data from a resume$0.0049$0.150

Debug a stack trace with context$0.0077$0.240

Per-call cost using published token counts for each task. Real-world prompts vary.

Add up to four models, tweak tasks live.