Mistral-Large-3-675B-Instruct-2512 — benchmark results

Mistral's open Large 3 sparse MoE (675B total, 41B active), December 2025. Provider: Mistral. Released 2025-12-02. Access: Open.

Unified ELO 1618 ± 23, rank #439 of 1776 rated models, from 14 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
RewardBench 2 Safety90.33Accuracy (%)84.3
RewardBench 2 Focus90.51Accuracy (%)77.5
Creative Writing v31400.2Elo score (self-reported)59.4
RewardBench 2 Factuality69.32Accuracy (%)51
Judgemark v2.168.2Judgemark Score (0-100)43.5
MATH-MC Level 297.39Accuracy (%)36.8
MATH-MC Level 593.94Accuracy (%)35.3
EQ-Bench Longform Writing48.3Writing Score (0-100)35.2
MATH-MC Level 196.98Accuracy (%)33.8
MATH-MC Level 396.68Accuracy (%)33.8
MATH-MC Level 495.75Accuracy (%)32.4
GSM-MC97.8Accuracy (%)32.1

Interactive version: theaggregate.ai/model?slug=mistral-large-3-675b-instruct-2512 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.