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

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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 ↗

LMArena

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

microsoft/phi-4 ↗

$0.07

Inference provider
deepInfra
Platform
DeepInfra
Unit
input_tokens_per_million
Currency
USD
Billing conditions

microsoft/phi-4 ↗

$0.14

Inference provider
deepInfra
Platform
DeepInfra
Unit
output_tokens_per_million
Currency
USD
Billing conditions

microsoft/phi-4 ↗

$0.07

Inference provider
openRouter
Platform
OpenRouter
Unit
input_tokens_per_million
Currency
USD
Billing conditions

microsoft/phi-4 ↗

$0.14

Inference provider
openRouter
Platform
OpenRouter
Unit
output_tokens_per_million
Currency
USD
Billing conditions

Provider specifications & access

1–7 / 7

microsoft/phi-4 ↗

source model id
azure-huggingface/microsoft--phi-4@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
MIT
context length
16384
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    microsoft/phi-4 ↗

    source model id
    azure-huggingface/microsoft--phi-4@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    MIT
    context length
    16384
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      microsoft/phi-4 ↗

      source model id
      azure-huggingface/microsoft--phi-4@3
      hosting
      foundry-managed-compute
      platforms
      • Microsoft Foundry
      license
      MIT
      context length
      16384
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities

        microsoft/phi-4 ↗

        source model id
        azure-huggingface/microsoft--phi-4@4
        hosting
        foundry-managed-compute
        platforms
        • Microsoft Foundry
        license
        MIT
        context length
        16384
        architecture
        input_modalities
        • text
        output_modalities
        • text
        capabilities

          microsoft/phi-4 ↗

          source model id
          azure-huggingface/microsoft--phi-4@5
          hosting
          foundry-managed-compute
          platforms
          • Microsoft Foundry
          license
          MIT
          context length
          16384
          architecture
          input_modalities
          • text
          output_modalities
          • text
          capabilities

            microsoft/phi-4 ↗

            source model id
            publishers/hf-microsoft/models/phi-4@001
            hosting
            vertex-self-deployed
            platforms
            • Google Cloud Vertex AI
            architecture
            input_modalities
            • text
            output_modalities
            • text
            capabilities

              Phi-4 ↗

              source model id
              publishers/microsoft/models/phi4@phi-4
              hosting
              vertex-self-deployed
              platforms
              • Google Cloud Vertex AI
              architecture
              input_modalities
              • text
              output_modalities
              • text
              capabilities

                Source specification observations

                1–8 / 8

                azureFoundry ↗

                field
                context_length
                value
                16384
                normalized value
                16384
                scope
                source-model
                source id
                azureFoundry
                confidence
                1

                azureFoundry ↗

                field
                context_length
                value
                16384
                normalized value
                16384
                scope
                source-model
                source id
                azureFoundry
                confidence
                1

                azureFoundry ↗

                field
                context_length
                value
                16384
                normalized value
                16384
                scope
                source-model
                source id
                azureFoundry
                confidence
                1

                azureFoundry ↗

                field
                context_length
                value
                16384
                normalized value
                16384
                scope
                source-model
                source id
                azureFoundry
                confidence
                1

                azureFoundry ↗

                field
                context_length
                value
                16384
                normalized value
                16384
                scope
                source-model
                source id
                azureFoundry
                confidence
                1

                openRouter ↗

                field
                context_length
                value
                16384
                normalized value
                16384
                scope
                source-model
                source id
                openRouter
                confidence
                1

                openRouter ↗

                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

                openRouter ↗

                field
                max_output_tokens
                value
                14745
                normalized value
                14745
                scope
                source-model
                source id
                openRouter
                confidence
                1

                Original sources

                1–20 / 22

                Hugging Face · Model repository ↗

                Hugging Face · microsoft/Phi-4 ↗

                DeepInfra · Model page ↗

                Google Cloud · Model page ↗

                Google Cloud · Model page ↗

                Microsoft Foundry · Model page ↗

                Microsoft Foundry · Model page ↗

                Microsoft Foundry · Model page ↗

                Microsoft Foundry · Model page ↗

                Microsoft Foundry · Model page ↗

                OpenRouter · Model page ↗

                Microsoft Foundry · Model documentation ↗

                arXiv · Model reference ↗

                DeepInfra · Catalog ↗

                Epoch AI · Catalog ↗

                GitHub · Catalog ↗

                Google Cloud · Catalog ↗

                Hugging Face · Catalog ↗

                Hugging Face · Catalog ↗

                LMArena · Catalog ↗

                Source links

                1–11 / 11

                Explore more models

                Models

                Loading
                EVIDENCE / COMPARISON

                Benchmarks

                Explore every benchmark

                Loading

                These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

                Install TensorTrace