Skip to main content
Van Data Team
Legacy modelMistral AI

Mistral Large 2 benchmarks, pricing and specs

Mistral Large 2 is a Mistral AI model released on July 24, 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 1314 Elo on Arena Text (Arena, measured October 8, 2026).

Context window
128K
Arena Text
1314 Elo

Data verified October 12, 2026 · Dataset 2026-10-12

Share this

Key facts

Provider
Mistral AI
Model family
Mistral Large
Release date
July 24, 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

Mistral Large 2 pricing

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

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 Text1314 EloNot rankedOctober 8, 2026Arena · 2026-10-12
GPQA Diamond49%Not rankedOctober 12, 2026Epoch AI · 2026-10-12

Strengths, cautions and best uses

Strengths

  • Mistral Large 2 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 general-purpose text trials with flexible deployment

Alternatives to Mistral Large 2

The closest current textmodels 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.

Mistral Large 2 FAQ

What is the context window of Mistral Large 2?

Mistral Large 2 accepts up to 128,000 tokens of context. That ranks #40 of 45 current text models by context length.

How does Mistral Large 2 score on independent benchmarks?

Mistral Large 2 scores 1314 Elo on Arena Text (Arena, measured October 8, 2026) and 49% on GPQA Diamond (Epoch AI, measured October 12, 2026). These are independent evaluations, not Mistral AI's own launch figures.

Is Mistral Large 2 open source or API only?

Mistral Large 2 is available both through Mistral AI's API and as open weights you can run yourself.

What are the best alternatives to Mistral Large 2?

The closest current alternatives by price and measured performance are DeepSeek-R1 (84 points higher on Arena Text, 1398 vs 1314), Gemini 2.5 Pro (131 points higher on Arena Text, 1445 vs 1314), GPT-4.1 (101 points higher on Arena Text, 1415 vs 1314) and GPT-4.1 mini (69 points higher on Arena Text, 1383 vs 1314).

Sources

Cite this page

Van Data Team. "Mistral Large 2 Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/mistral-large-2

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

Production evaluation

Deciding whether Mistral Large 2 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
Compare all modelsDiscuss your evaluation