LV
LLMversus

Codestral 22B vs Qwen 2.5 72B: Pricing, Benchmarks & Verdict (2026)

Pricing verified Apr 8, 2026

⚡ Quick Answer

Compare Codestral 22B and Qwen 2.5 72B across pricing, benchmarks, and capabilities.

Updated: April 8, 2026 · ✓ Pricing verified

Side-by-Side Comparison

FeatureCodestral 22BQwen 2.5 72B
ProviderMistral AIAlibaba
Input Price / 1M tokens$0.200$0.400
Output Price / 1M tokens$0.600$1.20
Context Window
256K
128K
Max Output Tokens
4,096
4,096
Arena ELON/A1,230
Coding ELO
1,250
1,210
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 Qwen 2.5 72B

Qwen 2.5 72B excels at coding, general-purpose tasks.

Strengths:

  • Strong code generation
  • Competitive pricing
  • Large context

Best for:

codinggeneral-purpose

Related Comparisons

Claude Opus 4 vs Qwen 2.5 72BClaude Opus 4 vs Codestral 22BGemini 2 5 Pro vs Qwen 2.5 72BCodestral 22B vs Gemini 2 5 ProO3 vs Qwen 2.5 72BCodestral 22B vs O3Deepseek R1 vs Qwen 2.5 72BCodestral 22B vs Deepseek R1O1 vs Qwen 2.5 72BCodestral 22B vs O1Qwen 2.5 72B vs Qwen 3 235bCodestral 22B vs Qwen 3 235bGemini Exp 1206 vs Qwen 2.5 72BCodestral 22B vs Gemini Exp 1206Gpt 4 5 vs Qwen 2.5 72BCodestral 22B vs Gpt 4 5Groq Deepseek R1 vs Qwen 2.5 72BCodestral 22B vs Groq Deepseek R1Llama 4 Maverick vs Qwen 2.5 72BCodestral 22B vs Llama 4 Maverick