AIBenchmarks
RankingsMistral Large 2
Mistral AIcodingreasoningmultilingualfunction-calling

Mistral Large 2

Mistral Large 2 delivers frontier performance with best-in-class multilingual support and EU-hosted GDPR compliance.

Arena ELO
1219
Avg Benchmark
78.0%
Context Window
128K
Speed
95 t/s
Latency P50
800ms
Input / 1M
$2

Capability Profile

Category scores across Coding, Math, Reasoning, Writing, Instructions, Hard Prompts

Benchmark Scores

MMLU84%
HumanEval92%
MATH69.9%
GSM8K93%
GPQA48%
BBH81.2%

Pros

Best-in-class multilingual (80+ languages)
EU-based GDPR compliance
Excellent HumanEval coding score

Cons

No vision capabilities
GPQA scores trail GPT-4o/Claude

Pricing

Free
Free
· Limited access via chat
Pay-as-you-go
Custom
· $2/1M input
· Full API
Enterprise
Custom
· EU hosting
· GDPR DPA
· SLA

Compare Mistral Large 2 With

Mistral Large 2 vs GPT-4oMistral Large 2 vs Claude 3.5 SonnetMistral Large 2 vs Gemini 1.5 Pro