How does phi 2 rank among AI models?
phi 2 is a superseded version and is not on the current board as of 2 October 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.
phi 2 is a language model from Microsoft. It has been superseded and no longer holds a position on ModelCap's current board. Its weights are openly downloadable.
Figures as of 2 Oct 2026, 03:44 UTC · download the public dataset · methodology
Superseded by Phi 4. It no longer holds a current-board position.
OpenRouter endpoint status could not be refreshed. This model is not treated as currently served until a successful observation arrives.
Input
Self-hosted
weights only · no listed API price
Output
Self-hosted
weights only · no listed API price
Context
—
tokens
Providers
0
endpoints
Providers
Uptime measured over the last 30 minutesCurrent provider status is unavailable.
Other versions (3)
ModelCap Index · All-versions archive
Methodology—
Not scored
Technical details
- Public rank basis
- Not scored (abstained)
- Evidence label
- Not scored · no public benchmark rows
- Index support
- 0.0% · not applicable
- Identity binding
- Exact catalogue product · microsoft/microsoft/phi-2 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata microsoft/phi-2@810d367871c1d460086d9f82db8696f2e0a0fcd0 (not the evaluation revision)
- Index observations used
- 0
- Architecture fallback
- abstained · 0% coverage · 0 anchors
Bayesian Evidence Score · measured evidence input only
BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.
- Observed capability
- —
- Evidence status
- No admitted measured evidence
- General preference
- —
- Coding
- —
- Agents & tools
- —
- Reasoning
- —
- Evidence breadth
- 0%
- Evidence coverage
- 0%
Market and catalogue signals · secondary, never the language Index rank
- Usage (OpenRouter popularity)
- —
- Liquidity (providers × uptime)
- —
- Open reach (HF downloads)
- 94.0
- Surface (context / tools / modalities)
- 0.0
- Freshness
- 2.0
- · HF 30d downloads 573878
- · Catalogue surface
- · First seen 2023-12-13
These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.
The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.
Experimental capability estimate
Estimate policy14.6
0.0–30.6 uncertainty interval
- Confidence
- 74%
- Training support
- 240 models · 137 lineages
- Out-of-domain check
- in domain
- Feature coverage
- 71%
- Lineage-held-out error
- 9.1 MAE
Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.
Deployment readiness
Metadata index47.9
partial · 52% metadata coverage
- Artifact reproducibility
- 85.0
- Access & legal clarity
- 100.0
- Deployability
- 8.0
- Evaluation provenance
- 0.0
Not yet published: the base model it derives from, a current serving provider, measured provider uptime, published provider pricing, declared context and output limits, admitted benchmark results, results across several capability areas, results from more than one source, a confident match to its benchmark entries, pinned evaluation dataset versions.
A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.
Market activity
Venue coverage- Market Gravity
- 14.2
- OpenRouter weekly popularity
- Not listed
Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.
Arena preference
No matched Arena rating
This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.
Market Gravity breakdown
- Usage55%
- 0.0
- Liquidity25%
- 0.0
- Open reach15%
- 94.0
- Freshness5%
- 2.0
OpenRouter weekly popularity across the full model catalogue.
Independent providers versus the model's open or closed cohort, weighted by uptime.
Hugging Face 30-day downloads for open models; neutral for closed models.
Time since first public availability, on a six-month half-life.
Specification
- Model ID
microsoft/phi-2- Inputs
- Text
- Outputs
- Text
- Cached input tokens
- Not offered
- First seen on OpenRouter
- 13 Dec 2023
Capabilities
- Not supported: Reasoning
- Not supported: Tool use
- Not supported: Structured output
- Not supported: Response format
- Not supported: Moderated
Weights & access
Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.
- Access
- Open weights
- Licence
- mit
- Pinned revision
- 810d367871c1
- Parameters
- 2.8B
- Architecture
- PhiForCausalLM
- Model type
- phi
- Hugging Face downloads (30d)
- 574K
- Downloads (all time)
- 23.5M
- Likes
- 4K
- Repository
- microsoft/phi-2
- Repository updated
- 8 Dec 2025, 11:35 UTC
phi 2: common questions
How much does phi 2 cost per 1M tokens?
No live API price is listed for phi 2 in the current snapshot as of 2 October 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.
Is phi 2 open-weight?
Open weights (mit). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is microsoft/phi-2 on Hugging Face.
When was phi 2 released?
phi 2 first appeared in the catalogue on 13 Dec 2023. It has since been superseded by Phi 4. Rank and price movements since then are recorded on the site's changes feed.