LLM compare · detail

Mistral Large 3

Provider: Mistral AI

Model type: specialist Budget: cheap at volume Use it for: sensitive deployments Use it for: document extraction Use it for: large batches

compliance pick backed by current AA.

Verdict „Mistral Large 3 has IQ 22.8 and input $0.5/M in the sources. Consider it for sensitive deployments, document extraction; for deep-frontier-reasoning, AI agents, run a second benchmark before rollout."

Snapshot summary

Mistral AI is a French lab with European positioning, a mix of open and commercial models and a practical deployment angle for regulated environments. Mistral Large 3 is the higher commercial model from Mistral AI. It makes sense when you want a European alternative for general reasoning, RAG and enterprise use.

In this compare snapshot it is tagged mainly for compliance, extraction, batch, with price tier cheap and context window není v ověřených datech. The negative side matters too: watch deep-frontier-reasoning, agents. Use the numbers below as the hard boundary, because this profile explains the model, it does not replace benchmark provenance.

Figures below, fetched from source artificial_analysis (fetched 2026-06-14T04:00:40Z).

Snapshot figures

$0.5/M input artificial_analysis:mistral-large-3

$1.5/M output artificial_analysis:mistral-large-3

22.8 intelligence index artificial_analysis:mistral-large-3

What this means

✓ Good for: compliance · extraction · batch

✗ Not for: deep-frontier-reasoning · agents

Source and provenance

Data source: artificial_analysis
Fetched: 2026-06-14T04:00:40Z
Status per metric: price: artificial_analysis:mistral-large-3; IQ: artificial_analysis:mistral-large-3; Elo: curated_seed; Aider: curated_seed; DeepSWE: curated_seed

This page shows only verified data from the current snapshot.