Mistral Large 4 Scores 13.3% on sudo L7 Software Engineering Benchmark

Key Info

Mistral Large 4 has been added to the sudo L7 leaderboard, a benchmark for staff-level software engineering, scoring 13.3% and beating Muse Spark 1.3 (12.2%) and Grok 4.7 (10.6%).

Highlights

• Mistral Large 4 scores 13.3% on sudo L7, ahead of Muse Spark 1.3 at 12.2% and Grok 4.7 at 10.6%
• sudo L7 evaluates whether coding agents can exercise the judgment of experienced engineers, not just write correct code
• The benchmark tests navigating messy systems, spotting hidden risks, and knowing when technically correct code is still wrong to ship
• The result places Mistral Large 4 at the top of the sudo L7 leaderboard among the compared models