← All Comparisons
Mistral Large 3 vs GLM-5
A detailed comparison of Mistral Large 3 (Mistral) and GLM-5 (Zhipu AI) across pricing, performance, and features.
Pricing Comparison
| Metric | Mistral Large 3 | GLM-5 | Difference |
|---|---|---|---|
| Input / 1M tokens | $2.00 | $1.00 | -50% |
| Output / 1M tokens | $5.00 | $3.20 | -36% |
| Context window | 128K | 200K | — |
| Max output | 16.384K | 128K | — |
Benchmark Comparison
| Benchmark | Mistral Large 3 | GLM-5 |
|---|---|---|
| MMLU-Pro | 83% | 70.4% |
| HumanEval | 91% | 91% |
| GPQA | — | 72% |
Capabilities
| Capability | Mistral Large 3 | GLM-5 |
|---|---|---|
| code | ✓ | ✓ |
| reasoning | ✓ | ✓ |
| text | ✓ | ✓ |
| tool-use | ✓ | ✓ |
| vision | ✓ | ✓ |
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
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: GLM-5 is the more affordable option at $1/$3.2 per 1M tokens.
Higher benchmarks: Mistral Large 3 scores higher on average across available benchmarks (87.0% avg).
Larger context: GLM-5 supports 200K tokens.
Choose GLM-5 if cost matters most. Choose Mistral Large 3 if you need the best possible quality for complex tasks.