Skip to content
ModelCap

Phi 3 mini 128k instruct

All-versions archive #3911 Arena configurationsOfficial publisher releaseOpen weights

Microsoft·microsoft/Phi-3-mini-128k-instruct

Phi 3 mini 128k instruct is ModelCap archive rank #391 (Measured), from the ModelCap Index as of 23 Sept 2026, 04:02 UTC.

Phi 3 mini 128k instruct weight access is open weights, from ModelCap classification of published repository metadata as of 23 Sept 2026, 04:02 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · All-versions archive
4.5#391
Measured · 57% support · score interval 0.0–9.9
Evidence as of 13 Sept 2026, 14:00 UTC
Market Gravity
13.9
Secondary market signal

Superseded by Phi 3.5 mini instruct. It no longer holds a current-board position; its all-versions archive rank is #391.

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
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes

Current provider status is unavailable.

Reasoning efforts

Best supported result can inform ModelCap

Published Max, X-High, High and other configurations for this model. These are sourced scores, not head-to-head essays.

Related community configurations

Human preference rating
ConfigurationRatingSource rankVotesSource
Default
phi-3-mini-128k-instruct
1129
CI 1122–1137
#37521KArena
Match 100%

Reported evaluation leads (1)

Not independent measurement

Structured rows reported in this exact model repository at the pinned revision below. They are the publisher talking about itself: never measured evidence, never a score input on their own. They remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
TIGER-Lab/MMLU-Pro
mmlu_pro
43.86
Unpinned
not published
Reported
Quarantined

Other versions (3)

ModelCap Index · All-versions archive

Methodology
4.5
Measured · 2 public benchmark observations across 2 boards
All-versions archive
#391
Public rank basis
Measured (measured)
Index support
56.9% · strong
Index interval
0.0–9.9
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
13 Sept 2026, 14:00 UTC
Identity binding
Exact catalogue product · microsoft/microsoft/Phi-3-mini-128k-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata microsoft/Phi-3-mini-128k-instruct@f3c06aed622e14ca0abf5115094e4fc9a9948f36 (not the evaluation revision)
Index observations used
2
Qualified Index evidence point
4.5
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
4.5
Evidence status
confirmed · 75% mass
General preference
4.5
Coding
4.8
Agents & tools
Reasoning
Evidence breadth
92%
Evidence coverage
57%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
Liquidity (providers × uptime)
Open reach (HF downloads)
91.2
Surface (context / tools / modalities)
0.0
Freshness
3.5
  • · HF 30d downloads 186308
  • · Catalogue surface
  • · First seen 2024-04-22

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

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.

Deployment readiness

Metadata index
58.2
partial · 70% metadata coverage
Not capability
Artifact reproducibility
85.0
Access & legal clarity
100.0
Deployability
8.0
Evaluation provenance
51.4

Missing: artifactReproducibility.base-lineage, deployability.independent-provider-records, deployability.measured-provider-uptime, deployability.published-provider-pricing, deployability.declared-capacity, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
13.9
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

Configuration results available

Arena has published current community results for Default. No default-configuration result is published, so the raw Arena field stays configuration-specific. The strongest supported result can still inform ModelCap Score with reduced confidence.

Current board through 13 Sept 2026, 14:00 UTC

Market Gravity breakdown

Usage55%
0.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
0.0

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
91.2

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
3.5

Time since first public availability, on a six-month half-life.

Specification

Context window
tokens
Max output
Inputs
Text
Outputs
Text
Tokenizer
Cached input tokens
Not offered
First seen on OpenRouter
22 Apr 2024

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
f3c06aed622e
Parameters
3.8B
Architecture
Phi3ForCausalLM
Model type
phi3
Hugging Face downloads (30d)
186K
Downloads (all time)
12.4M
Likes
2K
Repository updated
10 Dec 2025, 20:21 UTC

Benchmark leaderboards featuring Phi 3 mini 128k instruct

All leaderboards
Public benchmark boards on which Phi 3 mini 128k instruct has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena coding leaderboardArena (LMArena)11551142–1168#372 of 397Default13 Sept 2026

Phi 3 mini 128k instruct: common questions

How does Phi 3 mini 128k instruct rank among AI models?

Phi 3 mini 128k instruct is a superseded version and is not on the current board as of 23 September 2026. Its archive position, where one exists, is shown on the page; the newer version carries the current rank.

How much does Phi 3 mini 128k instruct cost per 1M tokens?

No live API price is listed for Phi 3 mini 128k instruct in the current snapshot as of 23 September 2026 because the latest endpoint refresh was unavailable. ModelCap shows a price only when a provider currently lists one.

Is Phi 3 mini 128k instruct 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-3-mini-128k-instruct on Hugging Face.

Which benchmarks has Phi 3 mini 128k instruct been evaluated on?

Phi 3 mini 128k instruct has published results on 1 public board tracked by ModelCap as of 23 September 2026: Arena coding 1155 (#372 of 397). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

When was Phi 3 mini 128k instruct released?

Phi 3 mini 128k instruct first appeared in the catalogue on 22 Apr 2024. It has since been superseded by Phi 3.5 mini instruct. Rank and price movements since then are recorded on the site's changes feed.