token.app › Compare › Gemma 2 27B vs Mistral Small 3

Gemma 2 27B vs Mistral Small 3

Mistral Small 3 leads on 2 of 2 shared benchmarks. Mistral Small 3 is 11× cheaper per token on a blended 3:1 basis. Mistral Small 3 accepts the larger context window (33K).

Head to head
Blended price uses a 3:1 input:output mix
Gemma 2 27BMistral Small 3
ProviderGoogleMistral AI
Input $/1M$0.650$0.050
Output $/1M$0.650$0.080
Blended $/1M$0.650$0.058
Context window8K33K
Max output2K16K
ReleasedJul 2024Jan 2025
LicenceOpen weightsOpen weights
GPQA Diamond 36.5% 45.3%
OTIS Mock AIME 1.4% 5.3%
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 Gemma 2 27B if…
  • No clear advantage on the data we hold.
Choose Mistral Small 3 if…
  • Costs less per token — $0.058 vs $0.650 blended
  • Higher GPQA Diamond (45.3% vs 36.5%)
  • Higher OTIS Mock AIME (5.3% vs 1.4%)
  • Larger context window (33K)
  • Newer model (released Jan 2025)
FAQ
Which is better, Gemma 2 27B or Mistral Small 3?
Across the 2 benchmarks both models have independently-run scores for, Gemma 2 27B leads on 0 and Mistral Small 3 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Gemma 2 27B cheaper than Mistral Small 3?
Mistral Small 3 is cheaper: $0.058 versus $0.650 per million tokens blended at 3:1 input:output. Input alone: $0.650 vs $0.050. Output alone: $0.650 vs $0.080.
What context windows do Gemma 2 27B and Mistral Small 3 have?
Gemma 2 27B: 8,192 tokens. Mistral Small 3: 32,768 tokens.
Who makes Gemma 2 27B and Mistral Small 3?
Gemma 2 27B is made by Google. Mistral Small 3 is made by Mistral AI.
Related comparisons