Comprehensive side-by-side LLM comparison
GLM 5 leads with 4.6% higher average benchmark score. Devstral-2-123B offers 60.1K more tokens in context window than GLM 5. GLM 5 is $0.64 cheaper per million tokens. Both models have their strengths depending on your specific coding needs.
Mistral AI
Devstral 2, released by Mistral AI on December 9, 2025, is a 123 billion parameter dense transformer model specifically designed for software engineering tasks. It features a 256K token context window and achieved 72.2% on SWE-bench Verified at release, making it a competitive open-weight option for automated coding and agentic development. Devstral 2 targets code generation, multi-file software engineering, and agentic development workflows under a modified MIT license.
Zhipu AI
GLM-5 is a large language model from Zhipu AI with 745 billion total parameters and 44 billion active parameters per inference, designed for agentic intelligence, advanced reasoning, and frontier-level performance. It features a 200K token context window and targets complex multi-step tasks requiring sustained reasoning and tool use. GLM-5 is available via Zhipu AI's Z.ai platform under an MIT license.
2 months newer

Devstral-2-123B
Mistral AI
2025-12-09
GLM 5
Zhipu AI
2026-02-11
Cost per million tokens (USD)
Devstral-2-123B
GLM 5
Context window and performance specifications
Average performance across 1 common benchmarks
Devstral-2-123B
GLM 5
Performance comparison across key benchmark categories
Devstral-2-123B
GLM 5
Available providers and their performance metrics
Devstral-2-123B
OpenRouter
GLM 5
Devstral-2-123B
GLM 5
Devstral-2-123B
GLM 5
Zhipu AI