Skip to content
ModelCap

Head-to-head comparison

Mistral Large 3 2512 vs Mistral Medium 3.5

Mistral Large 3 2512 (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 22 September 2026

As of 22 September 2026, Mistral Medium 3.5 holds the stronger ModelCap Index position (#63 vs #72); and Mistral Large 3 2512 is 10× cheaper per output token ($0.75/1M vs $7.50/1M).

Which should you choose?

Choose Mistral Large 3 2512 if…

  • API cost matters — $0.75/1M output tokens against $7.50/1M, about 10× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.25/1M against $1.50/1M.

Choose Mistral Medium 3.5 if…

  • you want the stronger overall ModelCap Index position — #63 against #72 (62.6 vs 60.9 points).
  • Arena coding is your yardstick — 1479 against 1469.
  • you want the more recently listed model — Mistral Medium 3.5 was listed 30 April 2026, Mistral Large 3 2512 1 December 2025.

Mistral Large 3 2512 vs Mistral Medium 3.5: specs, pricing and context

Specification comparison of Mistral Large 3 2512 and Mistral Medium 3.5
FieldMistral Large 3 2512Mistral AIMistral Medium 3.5Mistral AI
ModelCap Index position#72#63
Index score60.962.6
EvidenceMeasuredMeasured
Input price / 1M tokens$0.25$1.50
Output price / 1M tokens$0.75$7.50
Context window262K tokens262K tokens
Max output tokens210K210K
API providers listed11
Weight accessAPI onlyAPI only
Input modalitiesText, Image, FileText, Image, File
First listed1 December 202530 April 2026
PublisherMistral AIMistral AI

Evidence: 2 public benchmark observations across 2 boards · 4 public benchmark observations across 4 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Mistral Large 3 2512 vs Mistral Medium 3.5

Public benchmark boards where Mistral Large 3 2512 or Mistral Medium 3.5 has a published result
BoardMistral Large 3 2512Mistral Medium 3.5Leads
Arena codingArena (LMArena)14691464–147414791468–1490Mistral Medium 3.5
LMArena AgentLMArena—-10.9%-12.3%–-9.4%Only one result
AA Intelligence IndexArtificial Analysis—14.2intelligence-index:v4.3:reasoning-unspecifiedOnly one result
AA τ²-Bench TelecomArtificial Analysis—94.2%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Mistral Medium 3.5":reasoning=trueOnly one result
AA Humanity's Last ExamArtificial Analysis—13.8%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Mistral Medium 3.5":reasoning=trueOnly 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 3 2512 vs Mistral Medium 3.5: common questions

Is Mistral Large 3 2512 better than Mistral Medium 3.5?

Mistral Medium 3.5 ranks higher on the ModelCap Index as of 22 September 2026: #63 against #72. 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 3 2512 cheaper than Mistral Medium 3.5?

Mistral Large 3 2512 is cheaper on output tokens: $0.75/1M against $7.50/1M. Input tokens are $0.25/1M for Mistral Large 3 2512 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 $0.88 for Mistral Large 3 2512 versus $6.75 for Mistral Medium 3.5. Mistral Large 3 2512 costs 87.0% 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 3 2512 or Mistral Medium 3.5?

Both publish a 262K-token context window.

Which is better for coding, Mistral Large 3 2512 or Mistral Medium 3.5?

Arena coding: Mistral Large 3 2512 1469, Mistral Medium 3.5 1479 — Mistral Medium 3.5 leads.

Are Mistral Large 3 2512 and Mistral Medium 3.5 open-weight models?

Mistral Large 3 2512: API only. Mistral Medium 3.5: API only. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Mistral Large 3 2512 and Mistral Medium 3.5?

ModelCap currently lists 1 API provider for Mistral Large 3 2512 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 3 2512 vs Mistral Medium 3.5 comparison?

Every figure comes from the sealed ModelCap dataset published 22 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further