Model comparison · text

DeepSeek-R1 vs Phi-4-reasoning

Symmetrical, primary-source facts with unknown values left visible. No winner is assigned without comparable measurements.

FieldAt a glance
DeepSeek · activeDeepSeek-R1Verified Aug 28, 2026
Microsoft · activePhi-4-reasoningVerified Aug 28, 2026

Technical differences

Side-by-side facts

Indexable
FieldDeepSeek-R1Phi-4-reasoning
DeveloperDeepSeekMicrosoft
FamilyDeepseek R1Phi 4 Reasoning
ModelDeepSeek-R1Phi-4-reasoning
VersionDeepSeek-R1Phi-4-reasoning
Lifecycleactiveactive
Input modalitiesTextText
Output modalitiesTextText
Context window16384032768
Total parameters68453138600014659507200
Active parameters37000000000Unknown
Licensemitmit
Open weightsYesYes
API availableYesUnknown
Self-hostableYesYes
Capabilitieschat, generation, reasoningchat, generation, reasoning

13 comparable fields · 6 material differences · Pair passes the primary-source comparison gate

Primary benchmark evidence

Comparable performance

All benchmark results →
No protocol-matched benchmark yet.Results appear here only when both models share the same benchmark version, metric, evaluation protocol, and evidence class.

DeepSeek-R1 capabilities

chatgenerationreasoning
Input price$0.70
Output price$2.50
Serving providers1
Canonical IDdeepseek-ai/DeepSeek-R1

Phi-4-reasoning capabilities

chatgenerationreasoning
Input price
Output price
Serving providers0
Canonical IDmicrosoft/Phi-4-reasoning

Internal comparison graph

Related comparisons

All text comparisons →

Primary evidence

Sources and freshness