Skip to main content
BenchLM
Advertise

Model profile

Phi-4

MicrosoftEstablishedReleased Jan 1, 2025
Data verified
Overall Score
22.69Public #192 of 200Verified #91 of 99
Arena Elo
1256
Eligible category ranks
0of 8
Price (1M tokens)
$0 in / $0 out
API pricing
Speed
35tok/s
Context
16K

Evidence coverage

11 of 323 tracked benchmarks are published. 0 are verified and 11 provisional. 5 of 8 categories are measured.

Updated July 23, 2026Methodology
Published / tracked
11 / 323
Verified
0
Provisional
11
Categories with evidence
5 / 8

Evidence by category

  • Agentic1 benchmark
    Reported
  • Coding1 benchmark
    Reported
  • Reasoning2 benchmarks
    Reported
  • Knowledge6 benchmarks
    Reported
  • Math0 benchmarks
    Not measured
  • Multilingual0 benchmarks
    Not measured
  • Multimodal0 benchmarks
    Not measured
  • Inst. Following1 benchmark
    Reported
Open WeightSelf-hostNon-Reasoning
Confidence:
Low
base

Phi-4 ranks #192 out of 200 models on the public leaderboard with an overall score of 22.69/100. It also ranks #91 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Phi-4 is a open weight model with a 16K token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 11 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 20.32–25.12

  1. MiniMax M1 80k
    MiniMax
    #19025.12
    MiniMax M1 80k is #190 with a score of 25.12.
    Compare
  2. Llama 4 Maverick
    Meta
    #19123.49
    Llama 4 Maverick is #191 with a score of 23.49.
    Compare
  3. Phi-4Current model
    Microsoft
    #19222.69
    Phi-4 is #192 with a score of 22.69.
  4. Gemini 1.0 Pro
    Google
    #19321.78
    Gemini 1.0 Pro is #193 with a score of 21.78.
    Compare
  5. Claude 3 Haiku
    Anthropic
    #19421.39
    Claude 3 Haiku is #194 with a score of 21.39.
    Compare
  6. Ministral 3 8B
    Mistral
    #19520.96
    Ministral 3 8B is #195 with a score of 20.96.
    Compare
  7. Nova Pro
    Amazon
    #19620.32
    Nova Pro is #196 with a score of 20.32.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

No eligible category percentile is available from the published evidence yet.

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank Not rankedWeight 22%1 benchmarkReported38.1
CodingRank Not rankedWeight 20%1 benchmarkReported55.0
ReasoningRank Not rankedWeight 17%2 benchmarksReported31.3
KnowledgeRank Not rankedWeight 12%6 benchmarksReported56.1
MathWeight 5%0 benchmarksNot measuredNot measured
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalWeight 12%0 benchmarksNot measuredNot measured
Inst. FollowingWeight 5%1 benchmarkReportedScore pending

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1256±4.624,126
Coding1306±9.93,305
Math1265±10.42,764
Instruction Following1245±6.69,162
Creative Writing1210±9.74,062
Multi-turn1241±10.23,517
Hard Prompts1278±7.85,747
Hard Prompts (English)1290±9.33,804
Longer Query1266±10.82,896

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic1 benchmark
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Coding1 benchmark
AA-SciCodeReported

Artificial Analysis SciCode

26.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

0.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

0.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge6 benchmarks
Artificial Analysis Intelligence IndexReported
4.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

57.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

4.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-56.7%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

13.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

80.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

23.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

Frequently Asked Questions

How does Phi-4 perform overall in AI benchmarks?

Phi-4 has 11 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is Phi-4 good for knowledge and understanding?

Phi-4 has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Phi-4 good for coding and programming?

Phi-4 has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is Phi-4 good for reasoning and logic?

Phi-4 has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Phi-4 good for agentic tool use and computer tasks?

Phi-4 has visible benchmark coverage in agentic tool use and computer tasks, but BenchLM does not currently assign it a global category rank there.

Is Phi-4 good for instruction following?

Phi-4 has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Is Phi-4 open source?

Yes, Phi-4 is an open weight model created by Microsoft, meaning it can be downloaded and run locally or fine-tuned for specific use cases.

Does Phi-4 have full benchmark coverage on BenchLM?

Not yet. Phi-4 currently has 11 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Phi-4?

Phi-4 has a published context window of 16K, which determines how much text it can process in a single interaction.

Related Resources

More from Microsoft LLM Pricing Comparison BenchLM Methodology The AI Race Which LLM Should I Use? Benchmark Explainers
Last updated: July 23, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.