Pixtral Large: benchmark results

Mistral's 124B frontier multimodal model (November 2024) built on Mistral Large 2, with weights released under the research-only MRL license. Provider: Mistral. Released 2024-11-18. Access: Open.

Unified ELO 1525 ± 1, rank #572 of 1392 rated models, from 31 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LLM Stats (MM-MT-Bench)74Score (%)93.8
LLM Stats (AI2D)93.8Score (%)90.9
LLM Stats (ChartQA)88.1Score (%)76
LLM Stats (MathVista)69.4Score (%)62.2
LLM Stats (DocVQA)93.3Score (%)61.1
AI for Education Visual Reasoning - match (process)33.3Accuracy (%)44.6
AA TAU-2 Bench36.55Accuracy (%)44.5
ProLLM - Image Understanding55Score (%)34.6
ZEROBench-Sub18.68Score (self-reported)32.5
ZeroBench3Score (%)31.2
LLM Stats Score11.85LLM Stats Score (conservative rating)31.1
AI for Education Visual Reasoning - match (figure)36.1Accuracy (%)27.7

Interactive version: theaggregate.ai/model?slug=pixtral-large · How It Works · Data refreshed daily, snapshot 2026-09-05.