Microsoft: Phi 4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 …
microsoft/phi-4
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Specifications & capabilities
- Input
- text
- Output
- text
- Context window · tokens
- 16384
- Knowledge cutoff
- 2024-06-30
- Published model ID
- phi-4
- Capabilities
- structuredOutputs
Evaluations
21–40 / 83
1,269.853
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Spanish
- dimension
- style
- metric
- Arena rating
- rank
- 258
- sample size
- 127
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1218.1856435966292
- confidence upper
- 1321.519405118548
Original result ↗1,265.913
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control French
- dimension
- style
- metric
- Arena rating
- rank
- 258
- sample size
- 205
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1225.6187810550343
- confidence upper
- 1306.2064794895598
Original result ↗1,254.065
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Mathematical
- dimension
- general
- metric
- Arena rating
- rank
- 282
- sample size
- 2350
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1242.437242692983
- confidence upper
- 1265.691818866753
Original result ↗1,278.427
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Mathematical
- dimension
- style
- metric
- Arena rating
- rank
- 283
- sample size
- 2350
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1266.7559577188392
- confidence upper
- 1290.0971750960866
Original result ↗1,245.786
- source id
- lmarena
- leaderboard name
- LMArena Text Math
- dimension
- general
- metric
- Arena rating
- rank
- 284
- sample size
- 2764
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1235.28140712153
- confidence upper
- 1256.2908812678681
Original result ↗1,264.71
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Math
- dimension
- style
- metric
- Arena rating
- rank
- 289
- sample size
- 2764
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1254.189035981477
- confidence upper
- 1275.2304721705111
Original result ↗1,202.338
- source id
- lmarena
- leaderboard name
- LMArena Text Expert
- dimension
- general
- metric
- Arena rating
- rank
- 293
- sample size
- 1124
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1185.1119219811117
- confidence upper
- 1219.5648690112432
Original result ↗1,268.214
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Expert
- dimension
- style
- metric
- Arena rating
- rank
- 295
- sample size
- 1124
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1250.9184109165167
- confidence upper
- 1285.5095056807083
Original result ↗1,298.58
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Legal And Government
- dimension
- style
- metric
- Arena rating
- rank
- 301
- sample size
- 1341
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1281.9226552254167
- confidence upper
- 1315.2365603119679
Original result ↗1,241.096
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Legal And Government
- dimension
- general
- metric
- Arena rating
- rank
- 302
- sample size
- 1341
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1224.51943540099
- confidence upper
- 1257.6718556347307
Original result ↗1,201.705
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Medicine And Healthcare
- dimension
- general
- metric
- Arena rating
- rank
- 303
- sample size
- 1037
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1182.246563766753
- confidence upper
- 1221.1631575044046
Original result ↗1,231.167
- source id
- lmarena
- leaderboard name
- LMArena Text Coding
- dimension
- general
- metric
- Arena rating
- rank
- 304
- sample size
- 3305
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1221.3220721600044
- confidence upper
- 1241.0110586565288
Original result ↗1,229.793
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts English
- dimension
- general
- metric
- Arena rating
- rank
- 305
- sample size
- 3804
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1220.4063060607207
- confidence upper
- 1239.1790732348964
Original result ↗1,219.435
- source id
- lmarena
- leaderboard name
- LMArena Text Hard Prompts
- dimension
- general
- metric
- Arena rating
- rank
- 305
- sample size
- 5747
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1211.6707404079527
- confidence upper
- 1227.198710530317
Original result ↗1,211.619
- source id
- lmarena
- leaderboard name
- LMArena Text Chinese
- dimension
- general
- metric
- Arena rating
- rank
- 305
- sample size
- 1503
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1196.0797316549144
- confidence upper
- 1227.1583116793336
Original result ↗1,273.088
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Medicine And Healthcare
- dimension
- style
- metric
- Arena rating
- rank
- 306
- sample size
- 1037
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1253.6696671560755
- confidence upper
- 1292.5069043369683
Original result ↗1,289.116
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Hard Prompts English
- dimension
- style
- metric
- Arena rating
- rank
- 308
- sample size
- 3804
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1279.7267631212617
- confidence upper
- 1298.5055409421823
Original result ↗1,208.529
- source id
- lmarena
- leaderboard name
- LMArena Text Russian
- dimension
- general
- metric
- Arena rating
- rank
- 309
- sample size
- 2576
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1197.2831106320534
- confidence upper
- 1219.7741571609363
Original result ↗1,227.762
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Software And It Services
- dimension
- general
- metric
- Arena rating
- rank
- 310
- sample size
- 5580
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1219.706495675451
- confidence upper
- 1235.8182046589855
Original result ↗1,201.072
- source id
- lmarena
- leaderboard name
- LMArena Text Instruction Following
- dimension
- general
- metric
- Arena rating
- rank
- 311
- sample size
- 9162
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1194.450858073264
- confidence upper
- 1207.693165201289
Original result ↗Published prices
1–4 / 4
$0.07
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- input_tokens_per_million
- Currency
- USD
$0.14
- Inference provider
- deepInfra
- Platform
- DeepInfra
- Unit
- output_tokens_per_million
- Currency
- USD
$0.07
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- input_tokens_per_million
- Currency
- USD
$0.14
- Inference provider
- openRouter
- Platform
- OpenRouter
- Unit
- output_tokens_per_million
- Currency
- USD
Provider specifications & access
1–7 / 7
- source model id
- azure-huggingface/microsoft--phi-4@1
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 16384
- source model id
- azure-huggingface/microsoft--phi-4@2
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 16384
- source model id
- azure-huggingface/microsoft--phi-4@3
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 16384
- source model id
- azure-huggingface/microsoft--phi-4@4
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 16384
- source model id
- azure-huggingface/microsoft--phi-4@5
- hosting
- foundry-managed-compute
- license
- MIT
- context length
- 16384
- source model id
- publishers/hf-microsoft/models/phi-4@001
- hosting
- vertex-self-deployed
- source model id
- publishers/microsoft/models/phi4@phi-4
- hosting
- vertex-self-deployed
Source specification observations
1–8 / 8
- field
- context_length
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- azureFoundry
- confidence
- 1
- field
- context_length
- value
- 16384
- normalized value
- 16384
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- knowledge_cutoff
- reported field
- knowledge_cutoff
- value
- 2024-06-30
- normalized value
- 2024-06-30
- precision
- day
- scope
- source-model
- source id
- openRouter
- confidence
- 1
- field
- max_output_tokens
- value
- 14745
- normalized value
- 14745
- scope
- source-model
- source id
- openRouter
- confidence
- 1
Explore more models