Vision-language

Pixtral Large

By Mistral AI, in the Pixtral family.

Released
18 Nov 2024
Status
Retired
Retired
31 May 2026
Context
131.1K
Max output
—
Input per 1M tokens
$2.00
Output per 1M tokens
$6.00
Open weights
Yes
License
mistral-research-license
Parameters
124B
Knowledge cutoff
—
Reasoning
No
Modalities
image, text → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Human preference14.7Not ranked1 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Vision Arena (arena.ai)Arena score (Elo scale)1095Independent—28 Sep 2026Arena
Vision Arena (arena.ai)Votes5423Independent—28 Sep 2026Arena

Other Pixtral versions

Sources