← All Comparisons

GPT-5.2 Codex vs Mistral Large 3

A detailed comparison of GPT-5.2 Codex (OpenAI) and Mistral Large 3 (Mistral) across pricing, performance, and features.

Pricing Comparison

MetricGPT-5.2 CodexMistral Large 3Difference
Input / 1M tokens$1.75$2.00+14%
Output / 1M tokens$14.00$5.00-64%
Context window200K128K
Max output65.536K16.384K

Benchmark Comparison

BenchmarkGPT-5.2 CodexMistral Large 3
MMLU-Pro89%83%
HumanEval95.5%91%
GPQA76%

Capabilities

CapabilityGPT-5.2 CodexMistral Large 3
code
reasoning
text
tool-use
vision

GPT-5.2 Codex Strengths

  • Strong coding performance
  • Available via API now
  • 200K context window

GPT-5.2 Codex Weaknesses

  • Being superseded by 5.3
  • Higher output cost than some competitors

Mistral Large 3 Strengths

  • Low output cost ($5/1M) for a flagship
  • Strong multilingual support
  • European data sovereignty option

Mistral Large 3 Weaknesses

  • Lower benchmarks than top-tier competitors
  • Smaller ecosystem

Quick Verdict

Best value: Mistral Large 3 is the more affordable option at $2/$5 per 1M tokens.

Higher benchmarks: Mistral Large 3 scores higher on average across available benchmarks (87.0% avg).

Larger context: GPT-5.2 Codex supports 200K tokens.

Choose Mistral Large 3 if cost matters most. Choose GPT-5.2 Codex if you need the best possible quality for complex tasks.

More Comparisons