Skip to main content

Legacy model · Mistral AI

Ministral 8B benchmarks, pricing and specs

Ministral 8B is a Mistral AI model released on October 16, 2024 that takes text input and produces text. It is now listed as a legacy model. Its price is not published and accepts up to 128,000 tokens of context. It scores 1238 Elo on Arena Text (Arena, measured October 28, 2026).

Context window
128K#62 of 68 current models
Arena Text
1238 EloMeasured October 28, 2026

Data verified November 3, 2026 · Dataset 2026-11-06

Share this

Specs

Key facts

Provider
Mistral AI
Model family
Ministral
Release date
October 16, 2024
Status
Legacy
Access
API and open weights
API model id
Not reported
Context window
128,000 tokens
Max output
Not reported
Input
text
Output
text
Task families
text
Declared capabilities
reasoning

Charts

Against every current text model

Where Ministral 8B lands among the current models of its task, on every independent benchmark, on price and on context.

Where it stands

Ministral 8B is no longer a current model, so it is not ranked; each bar is the share of today's text models its value beats. Each bar is the share of current models it beats.

Ministral 8B among the current text models, one row per benchmark, price and context window.

Independent benchmarks

Arena Text

Not rankedno longer current

1,238 Elo · ahead of 0%

GPQA Diamond

Not rankedno longer current

27.1% · ahead of 0%

Price and context

Context window

Not rankedno longer current

128K tokens · longer than 0%

Price

Ministral 8B pricing

UnitPrice (USD)TierAppliesSource
1M input tokensNot reportedstandardCurrent
1M output tokensNot reportedstandardCurrent
1M input tokensNot reportedcachedCurrent

Benchmarks

Independent benchmark results

Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Mistral AI's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.

BenchmarkScoreRankMeasuredSource
Arena Text1238 EloNot rankedOctober 28, 2026Arena · 2026-11-03
GPQA Diamond27.1%Not rankedNovember 3, 2026Epoch AI · 2026-11-03

Fit

Strengths, cautions and best uses

Strengths
  • Ministral 8B records both API and open-weight access for text inputs and a published 128,000-token context window
Cautions
  • This record is marked legacy; confirm current availability and migration requirements before adoption
Best for
  • Historical compact open-weight or API text deployments

From benchmark to production

Building on Ministral 8B?

Public scores rarely hold on your own data. We test it against the alternatives on your real tasks, then build the agent or pipeline around the model that wins.

AI Model Cost AuditLaunch price $100, regular price $150What the audit includes

Alternatives

Alternatives to Ministral 8B

The closest current text models by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.

On score and price

Ministral 8B beside the 4 alternatives listed below, on Arena Text.

Ministral 8B and its alternatives on score and price.

Arena Text

Measured October 28, 2026, higher is better

Ministral 8B
1,238
DeepSeek-R1
1,398
GPT-4.1
1,415
GPT-4.1 mini
1,383
Qwen2.5-VL 72B Instruct
Not scored

FAQ

Ministral 8B FAQ

What is the context window of Ministral 8B?

Ministral 8B accepts up to 128,000 tokens of context. That ranks #62 of 68 current text models by context length.

How does Ministral 8B score on independent benchmarks?

Ministral 8B scores 1238 Elo on Arena Text (Arena, measured October 28, 2026) and 27.1% on GPQA Diamond (Epoch AI, measured November 3, 2026). These are independent evaluations, not Mistral AI's own launch figures.

Is Ministral 8B open source or API only?

Ministral 8B is available both through Mistral AI's API and as open weights you can run yourself.

What are the best alternatives to Ministral 8B?

The closest current alternatives by price and measured performance are DeepSeek-R1 (160 points higher on Arena Text, 1398 vs 1238), GPT-4.1 (177 points higher on Arena Text, 1415 vs 1238), GPT-4.1 mini (145 points higher on Arena Text, 1383 vs 1238) and Qwen2.5-VL 72B Instruct (from Alibaba Qwen).

Sources

Sources

All 255 sources behind the benchmarks, with their versions, licenses and notes, are in the source catalog.

Cite this page

Van Data Team. "Ministral 8B Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-11-06. https://vandatateam.com/ai-model-benchmarks/ministral-8b

Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.

Production evaluation

Deciding whether Ministral 8B fits your workload?

Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • Evaluation cases and acceptance thresholds tied to real work
  • Model routing, fallbacks and cost controls