Mistral: Models Intelligence, Performance & Price
This analysis is intended to support you in choosing the best model provided by Mistral for your use-case.
Most Intelligent
Mistral Large 4 Preview
GLM-5.2 (max)Mistral Medium 3.5Mistral Small 4Mistral Large 3Intelligence Index
Total 9 models
Fastest
GLM-5.2 (max)Ministral 3 3BMistral Small 4Mistral Small 4 (non-reasoning)Mistral Medium 3.5Output speed
Total 9 models
Lowest Price
Ministral 3 3BMinistral 3 8BMinistral 3 14BMistral Small 4Mistral Small 4 (non-reasoning)Blended price (per 1M tokens)
Total 9 models
Mistral offers 9 models, each with different intelligence, performance, and pricing characteristics. Below is a comparison of the key metrics across models.
- For intelligence, the top models on Mistral are Mistral Large 4 Preview (38), GLM-5.2 (max) (34), and Mistral Medium 3.5 (14).
- For output speed, the fastest models are GLM-5.2 (max) (246 t/s), Ministral 3 3B (208 t/s), and Mistral Small 4 (196 t/s). Speed varies significantly across models, with a 58% difference between the fastest and slowest.
- For latency, Ministral 3 3B (0.61s), Ministral 3 8B (0.74s), and Mistral Small 4 (non-reasoning) (0.80s) offer the lowest time to first answer token.
- For pricing, Ministral 3 3B ($0.04), Ministral 3 8B ($0.06), and Ministral 3 14B ($0.07) offer the lowest blended prices per 1M tokens. Prices vary up to 2.7x across models.
- For context window size, GLM-5.2 (max) (1M), Mistral Large 4 Preview (524k), and Mistral Medium 3.5 (262k) support the largest context windows on Mistral.
Intelligence Evaluations
Artificial Analysis Intelligence Index
Evaluations
Agentic knowledge work, (Elo-500)/2000
Knowledge
1 - hallucination rate
Agentic SaaS workflows
Agentic real-world work tasks, (Elo-500)/2000
Reasoning & knowledge
Professional document reasoning, All-pass
Agentic coding & terminal use
Long context reasoning
Coding
Physics reasoning
Agentic scientific research workflows in a terminal
Agentic software engineering in open-source repositories
Quantitative analysis on spreadsheets & documents
Legal agentic work, Hallucination-Gated All-Pass Rate
Agentic business operations
Kubernetes incident root-cause analysis
Medical long context reasoning
Visual reasoning
Intelligence Index vs. Price
Context Window
Context Window
Pricing
Intelligence Index vs. Price
Performance Summary
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
Cache Behaviour
Cache Hit Rate
Cost per Task vs. Cache Hit Rate
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time vs. Price
Further Analysis | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Mistral Large 4 Preview | 524k | Proprietary | 38 | $1.13 | 74 | 1.69 | 35.40 | 26.97 | |||
GLM-5.2 (max) | 1.05M | Open | 34 | $0.76 | 246 | 0.97 | 11.13 | 8.13 | |||
Mistral Medium 3.5 | 262k | Open | 14 | $0.50 | 155 | 2.33 | 18.40 | 12.86 | |||
Mistral Small 4 | 256k | Open | 11 | $0.02 | 196 | 0.74 | 13.51 | 10.21 | |||
Mistral Large 3 | 262k | Open | 9 | $0.03 | 78 | 1.09 | 7.51 | -- | |||
Mistral Small 4 (non-reasoning) | 262k | Open | 9* | -- | 176 | 0.80 | 3.64 | -- | |||
Ministral 3 14B | 262k | Open | 6 | $0.02 | 79 | 0.88 | 7.20 | -- | |||
Ministral 3 8B | 262k | Open | 5 | $0.01 | 90 | 0.74 | 6.27 | -- | |||
Ministral 3 3B | 131k | Open | 5 | $0.01 | 208 | 0.61 | 3.02 | -- | |||
Key definitions
Frequently Asked Questions
Common questions about Mistral
Mistral offers 9 models that we track: Mistral Large 4 Preview, GLM-5.2 (max), Mistral Medium 3.5, Mistral Small 4, Mistral Large 3, Mistral Small 4 (non-reasoning), Ministral 3 14B, Ministral 3 8B, and Ministral 3 3B.
The most intelligent model available on Mistral is Mistral Large 4 Preview with an Intelligence Index score of 38.
The fastest model on Mistral by output speed is GLM-5.2 (max) at 245.9 tokens per second.
The model with the lowest time to first answer token on Mistral is Ministral 3 3B at 0.61s. Lower latency means faster initial response time.
The most affordable model on Mistral by blended price is Ministral 3 3B at $0.04 per 1M tokens (7:2:1 cache hit/input/output ratio).
Prices on Mistral vary up to 31x across models, from $0.04 per 1M tokens for Ministral 3 3B to $1.16 per 1M tokens for Mistral Medium 3.5.
Yes, Mistral offers an OpenAI-compatible API, making it easy to switch from OpenAI or use existing OpenAI SDK integrations.
Yes, all 9 models on Mistral support JSON mode for structured output.
Yes, all 9 models on Mistral support function calling (tool use).
Yes, Mistral offers 4 reasoning models: Mistral Large 4 Preview, GLM-5.2 (max), Mistral Medium 3.5, and Mistral Small 4. Reasoning models use extended thinking to work through complex problems before providing an answer.
Yes, 8 of 9 models on Mistral are open weight models: GLM-5.2 (max), Mistral Medium 3.5, Mistral Small 4, Mistral Large 3, Mistral Small 4 (non-reasoning), Ministral 3 14B, Ministral 3 8B, and Ministral 3 3B.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
When choosing a model on Mistral, consider: intelligence (for quality-sensitive tasks), output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and features like context window size, JSON mode, or function calling support.