← All Comparisons

Mistral Medium 3 vs GLM-5

A detailed comparison of Mistral Medium 3 (Mistral) and GLM-5 (Zhipu AI) across pricing, performance, and features.

Pricing Comparison

MetricMistral Medium 3GLM-5Difference
Input / 1M tokens$0.40$1.00+150%
Output / 1M tokens$2.00$3.20+60%
Context window128K200K
Max output16.384K128K

Benchmark Comparison

BenchmarkMistral Medium 3GLM-5
MMLU-Pro76%70.4%
HumanEval87%91%
GPQA72%

Capabilities

CapabilityMistral Medium 3GLM-5
code
reasoning
text
tool-use
vision

Mistral Medium 3 Strengths

  • Very affordable for mid-tier quality
  • Good multilingual performance

Mistral Medium 3 Weaknesses

  • Lags behind on reasoning benchmarks
  • Smaller community and tooling

GLM-5 Strengths

  • Open-weight (MIT license) — self-hostable
  • 77.8% SWE-Bench Verified — top-tier coding
  • 128K max output — huge generation window

GLM-5 Weaknesses

  • MMLU-Pro lags behind Western flagships
  • 744B parameters — heavy to self-host
  • China-based — availability concerns

Quick Verdict

Best value: Mistral Medium 3 is the more affordable option at $0.4/$2 per 1M tokens.

Higher benchmarks: Mistral Medium 3 scores higher on average across available benchmarks (81.5% avg).

Larger context: GLM-5 supports 200K tokens.

Choose Mistral Medium 3 if cost matters most. Choose GLM-5 if you need the best possible quality for complex tasks.

More Comparisons