Mistral AI

Mistral Large 2

Zero-eval
#1MMLU French

by Mistral AI

+
+
+
+
About

Mistral Large 2 was introduced as the second generation of Mistral's flagship model, designed to provide frontier-level capabilities across diverse language tasks. Built with enhanced reasoning, coding, and multilingual abilities, it represents Mistral's most advanced offering for enterprise and demanding applications.

+
+
+
+
Pricing Range
Input (per 1M)$2.00 -$2.00
Output (per 1M)$6.00 -$6.00
Providers2
+
+
+
+
Timeline
AnnouncedJul 24, 2024
ReleasedJul 24, 2024
+
+
+
+
License & Family
License
Mistral Research License
Performance Overview
Performance metrics and category breakdown

Overall Performance

5 benchmarks
Average Score
87.6%
Best Score
93.0%
High Performers (80%+)
5

Performance Metrics

Max Context Window
256.0K
Avg Throughput
21.1 tok/s
Avg Latency
0ms
+
+
+
+
All Benchmark Results for Mistral Large 2
Complete list of benchmark scores with detailed information
GSM8k
text
0.93
93.0%
Self-reported
HumanEval
text
0.92
92.0%
Self-reported
MT-Bench
text
0.86
86.3%
Self-reported
MMLU
text
0.84
84.0%
Self-reported
MMLU French
text
0.83
82.8%
Self-reported
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+