LLMversus

Codestral 22B vs Gemma 2 27B: Pricing, Benchmarks & Verdict (2026)

Pricing verified Apr 20, 2026By LLMversusUpdated June 14, 2026View methodology

⚡ Quick Answer

Compare Codestral 22B and Gemma 2 27B across pricing, benchmarks, and capabilities.

Updated: April 20, 2026 · ✓ Pricing verified

Side-by-Side Comparison

FeatureCodestral 22BGemma 2 27B
ProviderMistral AIGoogle
Input Price / 1M tokens$0.300$0.650
Output Price / 1M tokens$0.900$0.650
Context Window
256K
8K
Max Output Tokens
4,096
4,096
Arena ELON/A1,190
Coding ELO
1,250
1,195
TTFT (ms)
150
150
Tokens/sec
100
100
MultimodalNoNo
JSON ModeYesYes
Function CallingYesYes
VisionNoNo
When to Use Codestral 22B

Codestral 22B excels at coding, long-context tasks.

Strengths:

  • Best-in-class code generation
  • Huge context for repos
  • Function calling strength

Best for:

codinglong-context
When to Use Gemma 2 27B

Gemma 2 27B excels at general-purpose, cost-effective tasks.

Strengths:

  • Good quality
  • Affordable
  • Open weights

Best for:

general-purposecost-effective

Related Comparisons

Claude Opus 4 vs Gemma 2 27BClaude Opus 4 vs Codestral 22BGemini 2 5 Pro vs Gemma 2 27BCodestral 22B vs Gemini 2 5 ProGemma 2 27B vs O3Codestral 22B vs O3Deepseek R1 vs Gemma 2 27BCodestral 22B vs Deepseek R1Gemma 2 27B vs O1Codestral 22B vs O1Gemma 2 27B vs Qwen 3 235bCodestral 22B vs Qwen 3 235bGemini Exp 1206 vs Gemma 2 27BCodestral 22B vs Gemini Exp 1206Gemma 2 27B vs Gpt 4 5Codestral 22B vs Gpt 4 5Gemma 2 27B vs Groq Deepseek R1Codestral 22B vs Groq Deepseek R1Gemma 2 27B vs Llama 4 MaverickCodestral 22B vs Llama 4 Maverick