GLM-5.2 (max) vs. Mistral Large 3
Comparison between GLM-5.2 (max) and Mistral Large 3 across intelligence, price, speed, context window and more.
For details relating to our methodology, see our Methodology page.
Highlights
Model Comparison
 Z AIGLM-5.2 (max) |  MistralMistral Large 3 | ||
|---|---|---|---|
| Intelligence Index | 53 | 16 | GLM-5.2 (max) is more intelligent than Mistral Large 3 |
| Price per 1M Tokens | $0.88 | $0.60 | Mistral Large 3 is cheaper than GLM-5.2 (max) |
| Output Speed | 107 tokens/s | 45 tokens/s | GLM-5.2 (max) is faster than Mistral Large 3 |
| Time to First Token | 1.38s | 1.19s | Mistral Large 3 responds faster than GLM-5.2 (max) |
| Context Window | 1000k tokens~1,500 A4 pages of size 12 Arial font | 256k tokens~384 A4 pages of size 12 Arial font | GLM-5.2 (max) has a larger context window than Mistral Large 3 |
| Release Date | June 2026 | December 2025 | GLM-5.2 (max) has a more recent release date than Mistral Large 3 |
| Parameters | 753B, 40B active at inference time | 675B, 41B active at inference time | GLM-5.2 (max) has more parameters than Mistral Large 3 |
| Reasoning | Yes | No | GLM-5.2 (max) has reasoning while Mistral Large 3 does not |
| Image Input Support | No | Yes | Mistral Large 3 has image input support while GLM-5.2 (max) does not |
| Open Source (Weights) | Both GLM-5.2 (max) and Mistral Large 3 are open source | ||
| License | |||
| License Supports Commercial Use Without Restrictions | Yes | Yes | Both GLM-5.2 (max) and Mistral Large 3 have license supports commercial use without restrictions |
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Evaluations
Agentic real-world work tasks, (Elo-500)/2000
Agentic tool use
Agentic coding & terminal use
Coding
Reasoning & knowledge
Scientific reasoning
Physics reasoning
Knowledge
1 - hallucination rate
Long context reasoning
Agentic knowledge work, Elo
Agentic SaaS workflows
Legal agentic work, criterion pass rate
Agentic business operations
Quantitative analysis on spreadsheets & documents
Instruction following
Long-horizon agentic tasks
Kubernetes incident root-cause analysis
Visual reasoning
AA-Briefcase
AA-Briefcase Elo
AA-Omniscience
AA-Omniscience Index
Openness Index
Artificial Analysis Openness Index: Score
Intelligence Index Comparisons
Intelligence Index vs. Cost per Intelligence Index Task
Token Use
Output Tokens per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Speed
Measured by Output Speed (tokens per second)
Output Speed
Time per Intelligence Index Task
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Frequently Asked Questions
GLM-5.2 (max) is more intelligent. GLM-5.2 (max) scores 53, compared with Mistral Large 3 at 16 on the Artificial Analysis Intelligence Index.
GLM-5.2 (max) is faster. GLM-5.2 (max) generates 107.5 tokens per second, compared with Mistral Large 3 at 44.8 tokens per second.
Mistral Large 3 is cheaper. Mistral Large 3 costs $0.60 per 1M tokens, compared with GLM-5.2 (max) at $0.88 per 1M tokens (7:2:1 cache hit/input/output ratio).
Mistral Large 3 has lower latency. Mistral Large 3 has a time to first token of 1.19s, compared with GLM-5.2 (max) at 1.38s.
GLM-5.2 (max) has a larger context window. GLM-5.2 (max) supports 1.0M tokens, compared with Mistral Large 3 at 260k tokens.