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
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (MM-MT-Bench) | 74 | Score (%) | 93.8 |
| LLM Stats (AI2D) | 93.8 | Score (%) | 90.9 |
| LLM Stats (ChartQA) | 88.1 | Score (%) | 76 |
| LLM Stats (MathVista) | 69.4 | Score (%) | 62.2 |
| LLM Stats (DocVQA) | 93.3 | Score (%) | 61.1 |
| AI for Education Visual Reasoning - match (process) | 33.3 | Accuracy (%) | 44.6 |
| AA TAU-2 Bench | 36.55 | Accuracy (%) | 44.5 |
| ProLLM - Image Understanding | 55 | Score (%) | 34.6 |
| ZEROBench-Sub | 18.68 | Score (self-reported) | 32.5 |
| ZeroBench | 3 | Score (%) | 31.2 |
| LLM Stats Score | 11.85 | LLM Stats Score (conservative rating) | 31.1 |
| AI for Education Visual Reasoning - match (figure) | 36.1 | Accuracy (%) | 27.7 |
Interactive version: theaggregate.ai/model?slug=pixtral-large · How It Works · Data refreshed daily, snapshot 2026-09-05.