Codestral (Jan '25): Intelligence, Performance & Price Analysis
Analysis of Mistral's Codestral (Jan '25) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
Comparison Summary
Intelligence:
Codestral (Jan '25) is of lower quality compared to average, with a MMLU score of 0.446 and a Intelligence Index across evaluations of 28.
Price:Codestral (Jan '25) is cheaper compared to average with a price of $0.45 per 1M Tokens (blended 3:1).
Codestral (Jan '25) Input token price: $0.30, Output token price: $0.90 per 1M Tokens.
Speed:Codestral (Jan '25) Input token price: $0.30, Output token price: $0.90 per 1M Tokens.
Codestral (Jan '25) is faster compared to average, with a output speed of 209.0 tokens per second.
Latency:Codestral (Jan '25) has a lower latency compared to average, taking 0.27s to receive the first token (TTFT).
Context Window:Codestral (Jan '25) has a smaller context windows than average, with a context window of 260k tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Further details
o1
Llama 3.3 Instruct 70B
Gemini 2.0 Pro Experimental (Feb '25)
Claude 3.5 Sonnet (Oct '24)
DeepSeek R1
Sonar
Nova Pro
Phi-4
Solar Mini
DBRX Instruct
MiniMax-Text-01
Llama 3.1 Nemotron Instruct 70B
Llama 3.1 Tulu3 405B
Reka Flash (Sep '24)
Command-R+ (Aug '24)
Jamba 1.5 Large
Qwen2.5 Max
Yi-Large
OpenChat 3.5 (1210)