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
61–80 / 83
1,233.102
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Non English
- dimension
- style
- metric
- Arena rating
- rank
- 324
- sample size
- 10025
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1226.6439645958287
- confidence upper
- 1239.5599462417779
Original result ↗1,229.299
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Writing And Literature And Language
- dimension
- style
- metric
- Arena rating
- rank
- 324
- sample size
- 6470
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1221.5011257695724
- confidence upper
- 1237.096563723558
Original result ↗1,210.023
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Creative Writing
- dimension
- style
- metric
- Arena rating
- rank
- 324
- sample size
- 4062
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1200.2752202976515
- confidence upper
- 1219.770079725275
Original result ↗1,161.941
- source id
- lmarena
- leaderboard name
- LMArena Text Industry Entertainment And Sports And Media
- dimension
- general
- metric
- Arena rating
- rank
- 324
- sample size
- 4486
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1152.9351307934817
- confidence upper
- 1170.947629553731
Original result ↗1,256.325
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Overall
- dimension
- style
- metric
- Arena rating
- rank
- 325
- sample size
- 24126
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1251.710886606828
- confidence upper
- 1260.9381252686603
Original result ↗1,156.782
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Exclude Ties
- dimension
- style
- metric
- Arena rating
- rank
- 325
- sample size
- 15789
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1148.969285568161
- confidence upper
- 1164.5954117445372
Original result ↗1,264.702
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Life And Physical And Social Science
- dimension
- style
- metric
- Arena rating
- rank
- 326
- sample size
- 4245
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1254.9843228796256
- confidence upper
- 1274.4190621228938
Original result ↗1,202.338
- source id
- lmarena
- leaderboard name
- LMArena Text Style Control Industry Entertainment And Sports And Media
- dimension
- style
- metric
- Arena rating
- rank
- 327
- sample size
- 4486
- evaluated at
- 2026-11-09T00:00:00.000Z
- source model id
- Phi-4
- confidence lower
- 1193.2563322024748
- confidence upper
- 1211.420077002828
Original result ↗52.95%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 MMLU-PRO · Raw
- dimension
- knowledge
- metric
- Raw accuracy
- rank
- 341
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 0.8783618221059865
- status
- archived
- precision
- float16
- task_count
- 6
- metric_kind
- Raw accuracy
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- false
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗47.723%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 MMLU-PRO · Normalized
- dimension
- knowledge
- metric
- Normalized score
- rank
- 341
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 0.8783618221059865
- status
- archived
- precision
- float16
- task_count
- 6
- metric_kind
- Normalized score
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- false
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗52.867%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 MMLU-PRO · Raw
- dimension
- knowledge
- metric
- Raw accuracy
- rank
- 354
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 2.7731595658140327
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Raw accuracy
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗47.63%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 MMLU-PRO · Normalized
- dimension
- knowledge
- metric
- Normalized score
- rank
- 354
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 2.7731595658140327
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Normalized score
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗31.647%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 MATH Lvl 5 · Raw
- dimension
- math
- metric
- Raw accuracy
- rank
- 767
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 2.7731595658140327
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Raw accuracy
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗31.647%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 MATH Lvl 5 · Normalized
- dimension
- math
- metric
- Normalized score
- rank
- 767
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 2.7731595658140327
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Normalized score
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗27.87%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 MATH Lvl 5 · Raw
- dimension
- math
- metric
- Raw accuracy
- rank
- 899
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 0.8783618221059865
- status
- archived
- precision
- float16
- task_count
- 6
- metric_kind
- Raw accuracy
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- false
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗27.87%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 MATH Lvl 5 · Normalized
- dimension
- math
- metric
- Normalized score
- rank
- 899
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 0.8783618221059865
- status
- archived
- precision
- float16
- task_count
- 6
- metric_kind
- Normalized score
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- false
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗30.358%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 Average
- dimension
- general
- metric
- Normalized six-task average
- rank
- 969
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 2.7731595658140327
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Normalized six-task average
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗29.483%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 Average
- dimension
- general
- metric
- Normalized six-task average
- rank
- 1112
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 0.8783618221059865
- status
- archived
- precision
- float16
- task_count
- 6
- metric_kind
- Normalized six-task average
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- false
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗5.853%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 IFEval · Normalized
- dimension
- instructionFollowing
- metric
- Normalized score
- rank
- 4528
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 2.7731595658140327
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Normalized score
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
Original result ↗5.853%
- source id
- openLLMLeaderboardV2
- leaderboard name
- Open LLM v2 IFEval · Raw
- dimension
- instructionFollowing
- metric
- Raw accuracy
- rank
- 4528
- aggregation scope
- suite
- Open LLM v2
- co2_kg
- 2.7731595658140327
- status
- archived
- precision
- bfloat16
- task_count
- 6
- metric_kind
- Raw accuracy
- rank_method
- Derived competition rank over published evaluations with reported scores, including variants and source flags
- weight_type
- Original
- published_at
- 2025-03-20T12:17:27Z
- chat_template
- true
- suite_version
- 2
- model_revision
- 381727a5ee103da6c1b14ecd3d39cd09832cbcf8
- source_flagged
- false
- dataset_revision
- 9c09a7cae43334062a82cb164f2ef255013dafa2
- metric_population
- 4576
- ranking_population
- 4576
- source_flag_anomaly
- false
- source model id
- microsoft/phi-4
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