BenchLeader

DeepSeek vs Thinking Machines

Verdict
  • Their flagships are level: DeepSeek V4.1 Flash 58.5 vs Inkling 2 Small 57.9.
  • DeepSeek has the better model in 3 of 4 price bands.
  • DeepSeek's fastest ranked model (DeepSeek V4.1 Flash, 240 tok/s) beats Thinking Machines's (Inkling Small, 116 tok/s).
  • DeepSeek publishes more open-weights models (26 vs 2).

Best model per price band

Each provider’s highest-index model below the price ceiling. Purple marks the winner of the band.

Price bandDeepSeekThinking Machines
Under $0.50/MDeepSeek V4 Flash high 57.2$0.262/MInkling 2 Small 57.9$0.475/M
Under $2/MDeepSeek V4.1 Flash max 58.5$0.525/MInkling 2 Small 57.9$0.475/M
Under $10/MDeepSeek V4.1 Flash max 58.5$0.525/MInkling 2 Small 57.9$0.475/M
Any priceDeepSeek V4.1 Flash max 58.5$0.525/MInkling 2 Small 57.9$0.475/M

Line-up

MetricDeepSeekThinking Machines
Flagship index58.557.9
Ranked models173
Open-weights models262
Cheapest ranked, $/M$0.068$0.475
Fastest ranked, tok/s240116
Release cadence, days37–
Last release17 Oct 2026–
Next expected8 Nov 2026 – 7 Dec 2026–

Data as of 16 Nov 2026. See DeepSeek and Thinking Machines in full.