Compare
DeepSeek R2 vs GPT-5 Turbo
DeepSeek vs OpenAI. Specs, benchmarks, and real per-task cost — all in one page.
Verdict
DeepSeek R2 is ~10.9× cheaper on a 3:1 input:output blend. DeepSeek R2 is open-weights, the other is proprietary.
DeepSeek
DeepSeek R2DeepSeek’s reasoning variant. Competes with o4 on math at a fraction of the cost.
Frontier math at open-weights pricingLong CoT traces
OpenAI
GPT-5 TurboOpenAI’s flagship unified model. Handles text, vision, and audio natively. The generalist benchmark champion.
Native multimodalStrong math and scienceHuge ecosystem
Pricing
Input / 1M$0.55$6.00
Output / 1M$2.19$24.00
Context128K400K
Max output64K32K
LicenseOpen weightsProprietary
Released2026-01-152026-01-21
Benchmarks
LMSYS ELO—1398.0
MMLU Pro87.891.2
HumanEval90.193.0
SWE-Bench—65.8
MATH94.191.5
GPQA71.268.1
MMMU—78.8
IFEval—88.9
Per-task cost
Summarize a 1-hour meeting transcript$0.0093$0.102
Review a 500-line pull request$0.0088$0.096
Answer a customer support ticket$0.0034$0.037
Extract structured data from a resume$0.0049$0.054
Debug a stack trace with context$0.0077$0.084
Per-call cost using published token counts for each task. Real-world prompts vary.