token.app โ€บ Compare โ€บ Mixtral 8x22B Instruct vs Mistral Small 3

Mixtral 8x22B Instruct vs Mistral Small 3

Mistral Small 3 leads on 1 of 1 shared benchmarks. Mistral Small 3 is 52ร— cheaper per token on a blended 3:1 basis. Mixtral 8x22B Instruct accepts the larger context window (66K).

Head to head
Blended price uses a 3:1 input:output mix
Mixtral 8x22B InstructMistral Small 3
ProviderMistral AIMistral AI
Input $/1M$2.00$0.050
Output $/1M$6.00$0.080
Blended $/1M$3.00$0.058
Context window66K33K
Max outputโ€”16K
ReleasedApr 2024Jan 2025
LicenceOpen weightsOpen weights
GPQA Diamond 34.1% 45.3%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Mixtral 8x22B Instruct ifโ€ฆ
  • Larger context window (66K)
Choose Mistral Small 3 ifโ€ฆ
  • Costs less per token โ€” $0.058 vs $3.00 blended
  • Higher GPQA Diamond (45.3% vs 34.1%)
  • Newer model (released Jan 2025)
FAQ
Which is better, Mixtral 8x22B Instruct or Mistral Small 3?
Across the 1 benchmark both models have independently-run scores for, Mixtral 8x22B Instruct leads on 0 and Mistral Small 3 leads on 1. Benchmarks are one input โ€” price and context window are on this page too.
Is Mixtral 8x22B Instruct cheaper than Mistral Small 3?
Mistral Small 3 is cheaper: $0.058 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $2.00 vs $0.050. Output alone: $6.00 vs $0.080.
What context windows do Mixtral 8x22B Instruct and Mistral Small 3 have?
Mixtral 8x22B Instruct: 65,536 tokens. Mistral Small 3: 32,768 tokens.
Who makes Mixtral 8x22B Instruct and Mistral Small 3?
Mixtral 8x22B Instruct is made by Mistral AI. Mistral Small 3 is made by Mistral AI.
Related comparisons