Mistral Large
Mistral AILLMs
87.1
Performance
★ 4.3
Rating
312
Reviews
Text GenerationSmallReasoningProprietary
About
Mistral AI's flagship model with strong multilingual capabilities and reasoning, designed for enterprise applications.
Strengths
Excellent balance of reasoning and multilingual ability supporting 12+ languages natively. Strong at code and math. Trusted for EU data sovereignty with European hosting. Competitive for production use cases where multilingual support matters.
Specifications
- Context window
- 128,000
- Parameters
- —
Pricing
- Input cost
- $2.00 / 1M
- Output cost
- $6.00 / 1M
$2.00 input / $6.00 output per 1M tokens
Speed & Latency
- 146
- tokens/sec
- 443ms
- time to first token
- 300 RPM
- rate limits
Available On
Mistral APIAzure AIAmazon BedrockGoogle Vertex AI
Features
function callingstreamingjson modesystem messages
Performance Trend
Benchmark score trends over time for the top 5 benchmarks.
Loading history...
Benchmarks
Scores from various benchmark tests; higher is better.
| Test | Score | Percentile | Source |
|---|---|---|---|
| ARC-Challenge | 94.0 | — | huggingface |
| BigBench Hard | 80.1 | p91 | seed |
| Chatbot Arena ELO | 1270.0 | — | chatbot-arena |