Data as of October 20, 2026 · How the score is built
Released Dec 12, 202416K context
Phi-4
Decision readingPhi-4 scores 25 out of 100 and ranks #211 of 228. This profile shows 5 source-displayable benchmark rows; its strongest eligible category is Multilingual at #17. Published weights can be self-hosted, but infrastructure cost varies and is not a comparable API token rate.
Released Dec 12, 2024 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
25/100
field median 49.9#211 of 228 ranked models
Public
#211of 228
Verified #83 of 87
Price
Self-hosted; infrastructure cost varies
input median $0.72No comparable first-party hosted token rate
Speed
41tok/s
field median 93.5 tok/sFirst token 2.54 s
Context
16Ktokens
field median 256,000Reported for this model; direct source link not stored
Strongest published evidence
Multilingual ranks #17. A well-rounded choice across a range of tasks.
Validate before choosing
5 published rows leave some tracked benchmark slots empty. No comparable first-party API token rate is published.
Source-linked · 5 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| CodingWeight 20%1 benchmarkVerified | Score pending | 1 benchmark | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeRank #180 of 187Percentile 4thWeight 12%2 benchmarksVerified | 23.2 | 2 benchmarks | Verified | |||
| MultilingualRank #17 of 17Percentile 0thWeight 7%2 benchmarksVerified | 1.0 | 2 benchmarks | Verified | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
5 of 728 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- AgenticNot measured
- Coding1/1 verified
- ReasoningNot measured
- MultimodalNot measured
- Knowledge2/2 verified
- Multilingual2/2 verified
- Inst. FollowingNot measured
- MathNot measured
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
Phi-4 category percentile values
- AgenticNot eligible
- CodingNot eligible
- ReasoningNot eligible
- MultimodalNot eligible
- Knowledge4th percentile
- Multilingual0th percentile
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- AgenticNot ranked
- CodingNot ranked
- ReasoningNot ranked
- MultimodalNot ranked
- Knowledge#180/187
- Multilingual#17/17
- Inst. FollowingNot ranked
- MathNot ranked
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HumanEvalEvaluating Large Language Models Trained on Code | Score82.6% | Versus best verified row Best verified: o4-mini · 97.3% | Gap14.7 behind | WeightDisplay only | Provider exact |
Knowledge2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| GPQAGraduate-Level Google-Proof Q&A | Score56.1% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap39.9 behind | Weight3% ref. weight | Provider exact |
| MMLUMassive Multitask Language Understanding | Score84.8% | Versus best verified row Best verified: o1 · 91.8% | Gap7 behind | WeightDisplay only | Provider exact |
Multilingual2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMLU-ProX | Score49.9% | Versus best verified row Best verified: Qwen3.7 Max · 87% | Gap37.1 behind | WeightWeighted 100% | |
| MGSMMultilingual Grade School Math | Score80.6% | Versus best verified row Best verified: o4-mini · 93.7% | Gap13.1 behind | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 5 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- Not published
- Context window
- 16K
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not sourced yet
- Availability
- Not sourced yet
- Cloud regions
- Not tracked yet
- Lifecycle
- Established
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing record
- Self-host
- Open weights available; hardware estimate not sourced
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
Phi-4 ranks #211 of 228 on the public leaderboard with a score of 24.97/100. Its source-verified position is #83 of 87.
Phi-4 is a open weight model with a 16K context window. No explicit reasoning mode is documented in this profile.
5 of 728 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multilingual at #17, while its lowest eligible position is Knowledge at #180. a well-rounded choice across a range of tasks.
Last updated October 20, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run Phi-4 by API
2 hosts publish a per-token price for it. DeepInfra has the lowest output rate, $0.14 per million tokens. Prices read from each host’s own pages on October 20, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context |
|---|---|---|---|---|
| DeepInfra | $0.07 | $0.14 | — | 16K |
| OpenRouter | $0.07 | $0.14 | — | 16K |
Published weights are available, but BenchLM does not yet have a sourced parameter and VRAM profile for this exact model. Hardware cost estimates stay unavailable until that sizing record is complete.
Estimate VRAM from known parametersQuestions
How does Phi-4 perform overall in AI benchmarks?
Phi-4 ranks #211 out of 228 models on the public BenchAlign leaderboard, with a score of 24.97/100. Its evidence status is Supported, and this profile shows 5 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is Phi-4 good for knowledge and understanding?
Phi-4 ranks #180 out of 187 eligible models for knowledge and understanding, with a public category score of 23.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Phi-4 good for coding and programming?
Phi-4 has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Phi-4 good for multilingual tasks?
Phi-4 ranks #17 out of 17 eligible models for multilingual tasks, with a public category score of 1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is Phi-4 open source?
Phi-4 is an open-weight model from Microsoft. Its weights can be downloaded for local or hosted deployment, subject to the published license. Open weight does not automatically mean open source: training data and training code may remain private, and commercial restrictions can still apply.
Does Phi-4 have full benchmark coverage on BenchLM?
No. Phi-4 currently has 15 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Phi-4?
Phi-4 has a reported context window of 16K in the exact-model catalog record. The value stays visible, but the profile marks its source link as unavailable instead of presenting it as directly documented. Maximum output length remains separate because providers often publish a different limit.