Skip to content
ModelCap

Mistral Small 3.1 24B

All-versions archive #140Arena #256Open weights

Mistral AI·mistralai/mistral-small-3.1-24b-instruct

Mistral Small 3.1 24B is a language model published by Mistral AI. 1 OpenRouter endpoint is published in the latest snapshot. It accepts text, image input and returns text. The published context limit is 128K tokens.

ModelCap Index · All-versions archive
38.2#140
Measured · 82% support · score interval 38.2–45.2
Market Gravity
33.0
Secondary market signal

Superseded by Mistral Small 3.2 24B. It no longer holds a current-board position; its all-versions archive rank is #140.

Input
$0.351
per 1M tokens
Output
$0.555
per 1M tokens
Context
128K
tokens
Providers
1
endpoint
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Cloudflare$0.351$0.555128K—100.0%

Reported evaluation leads (1)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
TIGER-Lab/MMLU-Pro
mmlu_pro
—66.8
Unpinned
not published
Reported
Quarantined

Other versions (1)

ModelCap Index · All-versions archive

Methodology
38.2
Measured · 2 public benchmark observations across 2 boards
All-versions archive
#140
Public rank basis
Measured (measured)
Index support
81.6% · strong
Index interval
38.2–45.2
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · mistralai/mistralai/mistral-small-3.1-24b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata mistralai/Mistral-Small-3.1-24B-Instruct-2503@68faf511d618ef198fef186659617cfd2eb8e33a (not the evaluation revision)
Direct benchmark observations
2
Breadth-adjusted BES point estimate
41.7
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
41.7
Evidence status
confirmed · 83% mass
General preference
40.5
Coding
46.6
Agents & tools
—
Reasoning
—
Evidence breadth
92%
Evidence coverage
82%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
4.5
Liquidity (providers × uptime)
77.8
Open reach (HF downloads)
69.0
Surface (context / tools / modalities)
40.0
Freshness
14.4
  • · OpenRouter popularity #231
  • · 1 live provider
  • · HF 30d downloads 291441
  • · Catalogue: context 128000, modalities Text/Image
  • · First seen 2025-03-17

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
80.8
strong · 98% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
68.0
Evaluation provenance
52.2

Missing: 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
33.0
OpenRouter weekly popularity
#231 of 298

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

Status
Ranked
Source
Arena
Official rank
#256 of 385
Rating
1303.3
95% confidence interval
1299–1308
Votes
33K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
98%

Market Gravity breakdown

Usage55%
4.5

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
77.8

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

Open reach15%
69.0

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

Freshness5%
14.4

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

Specification

Context window
128K tokens
Max output
128K tokens
Inputs
Text, Image
Outputs
Text
Tokenizer
Mistral
Cached input tokens
Not offered
First seen on OpenRouter
17 Mar 2025
Knowledge cutoff
2023-10-31

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
apache-2.0
Pinned revision
68faf511d618
Parameters
24.0B
Architecture
Mistral3ForConditionalGeneration
Model type
mistral3
Hugging Face downloads (30d)
291K
Downloads (all time)
3.8M
Likes
1K
Repository
mistralai/Mistral-Small-3.1-24B-Instruct-2503
Repository updated
22 Dec 2025, 10:15 UTC
Base lineage
mistralai/Mistral-Small-3.1-24B-Base-2503