Skip to content
ModelCap

Head-to-head comparison

Mistral Large 4 vs Mistral Medium 3.5

Mistral Large 4 (Mistral AI) and Mistral Medium 3.5 (Mistral AI) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 11 October 2026

As of 11 October 2026, Mistral Large 4 holds the stronger ModelCap Index position (#62 vs #73); Mistral Large 4 is 3.6× cheaper per output token ($2.09/1M vs $7.50/1M); and Mistral Large 4 offers the longer context window (1M vs 262K tokens).

Which should you choose?

Choose Mistral Large 4 if…

  • you want the stronger overall ModelCap Index position — #62 against #73 (63.1 vs 60.8 points).
  • API cost matters — $2.09/1M output tokens against $7.50/1M, about 3.6× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.68/1M against $1.50/1M.
  • you need the longer context window — 1M tokens against 262K.
  • Arena text is your yardstick — 1429 against 1426.
  • Arena coding is your yardstick — 1492 against 1478.
  • LMArena Agent is your yardstick — -6.6% against -12.6%.
  • you want the more recently listed model — Mistral Large 4 was listed 6 October 2026, Mistral Medium 3.5 30 April 2026.

Choose Mistral Medium 3.5 if…

  • ModelCap publishes no field on which Mistral Medium 3.5 leads Mistral Large 4 for this pair.

Mistral Large 4 vs Mistral Medium 3.5: specs, pricing and context

Specification comparison of Mistral Large 4 and Mistral Medium 3.5
FieldMistral Large 4Mistral AIMistral Medium 3.5Mistral AI
ModelCap Index position#62#73
Index score63.160.8
EvidenceMeasuredMeasured
Input price / 1M tokens$0.68$1.50
Output price / 1M tokens$2.09$7.50
Context window1M tokens262K tokens
Declared route output cap262K210K
API providers listed11
Weight accessNo linked weightsNo linked weights
Input modalitiesText, ImageText, Image, File
First listed6 October 202630 April 2026
PublisherMistral AIMistral AI

Evidence: 3 public benchmark observations across 3 boards · 3 public benchmark observations across 3 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Mistral Large 4 vs Mistral Medium 3.5

Public benchmark boards where Mistral Large 4 or Mistral Medium 3.5 has a published result
BoardMistral Large 4Mistral Medium 3.5Leads
Arena textArena (LMArena)14291420–1439Not reported14261420–1433Not reportedMistral Large 4
Arena codingArena (LMArena)14921473–151214781467–1489Mistral Large 4
LMArena AgentLMArena-6.6%-9.5%–-3.6%-12.6%-14.1%–-11.1%Mistral Large 4
AA Intelligence IndexArtificial Analysis—14.2ReasoningOnly one result
AA Terminal-Bench 2.1Artificial Analysis—50.6%ReasoningOnly one result
AA τ²-Bench TelecomArtificial Analysis—94.2%ReasoningOnly one result
AA Humanity's Last ExamArtificial Analysis—13.8%ReasoningOnly one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Mistral Large 4 vs Mistral Medium 3.5: common questions

Is Mistral Large 4 better than Mistral Medium 3.5?

Mistral Large 4 ranks higher on the ModelCap Index as of 11 October 2026: #62 against #73. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is Mistral Large 4 cheaper than Mistral Medium 3.5?

Mistral Large 4 is cheaper on output tokens: $2.09/1M against $7.50/1M. Input tokens are $0.68/1M for Mistral Large 4 and $1.50/1M for Mistral Medium 3.5. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $2.40 for Mistral Large 4 versus $6.75 for Mistral Medium 3.5. Mistral Large 4 costs 64.4% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, Mistral Large 4 or Mistral Medium 3.5?

Mistral Large 4 has the larger context window: 1M tokens against 262K. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified.

Which is better for coding, Mistral Large 4 or Mistral Medium 3.5?

Arena coding: Mistral Large 4 1492, Mistral Medium 3.5 1478 — Mistral Large 4 leads.

Are Mistral Large 4 and Mistral Medium 3.5 open-weight models?

Mistral Large 4: No linked weights. Mistral Medium 3.5: No linked weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence. A missing weight link does not identify every API or chat product that offers a model.

Where can I run Mistral Large 4 and Mistral Medium 3.5?

ModelCap currently lists 1 API provider for Mistral Large 4 and 1 for Mistral Medium 3.5, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Mistral Large 4 vs Mistral Medium 3.5 comparison?

Every figure and ModelCap Index position comes from the same published snapshot dated 11 October 2026. Publication and page updates happen separately; use the snapshot date shown on the page.

Explore further