DeepSeek Chat V3 vs Codestral

Performance benchmarks + pricing comparison — updated April 2026

DeepSeek Chat V3

DeepSeek

Very affordable general-purpose model from DeepSeek. Strong coding and reasoning at low cost.

Input$0.270/M
Output$1.10/M
Context128K tokens
Best ForCost-sensitive projects, coding, general tasks
Benchmark62/100

Codestral

Mistral

Mistral's dedicated coding model. Open-weight and highly optimized for code generation and completion.

Input$0.300/M
Output$0.900/M
Context128K tokens
Best ForCode completion, code generation, IDE integration
Benchmark60/100

Benchmark Performance Comparison

Third-party benchmark scores — higher is better. Data sourced from SWE-bench, LiveCodeBench, HumanEval, and BigCodeBench.

BenchmarkDeepSeek Chat V3CodestralLeader
Overall Score 62 60 DeepSeek Chat (V3) leads by 2pts
SWE-bench Verified 56 54 DeepSeek Chat (V3) leads by 2pts
LiveCodeBench 64 64 DeepSeek Chat (V3) leads by 0pts
HumanEval 84 82 DeepSeek Chat (V3) leads by 2pts
BigCodeBench 46 44 DeepSeek Chat (V3) leads by 2pts

Cost Comparison by Scenario

Estimated cost per project with 30% cache hit rate. Actual costs may vary based on usage patterns.

ScenarioDeepSeek Chat V3CodestralSavings
Small Script (1K lines) $0.04 $0.04 Codestral saves <$0.01 (12%)
Medium Feature (10K lines) $0.31 $0.29 Codestral saves $0.03 (9%)
Large Project (50K lines) $1.57 $1.43 Codestral saves $0.15 (9%)
Code Review (5K lines) $0.07 $0.07 DeepSeek Chat V3 saves <$0.01 (0%)

Value Analysis (Price per Benchmark Score Point)

Lower is better — how much you pay for each point of benchmark performance.

ModelOverall ScorePrice per Score PointVerdict
DeepSeek Chat V3 62 $0.004/pt Better value
Codestral 60 $0.005/pt Higher cost per point

DeepSeek Chat V3 delivers the best value at $0.004 per score point.

Strengths & Weaknesses

DeepSeek Chat V3

  • + Excellent value
  • + Strong coding focus
  • - Less general-purpose

Codestral

  • + Code-specialized
  • + Very cheap
  • - Narrow focus

Verdict

DeepSeek Chat V3 wins on both price and performance — $0.270/M input with a benchmark score of 62/100.

For most developers, this is the clear choice between these two models.

Compare with Other Models