ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
4 models
Mistral AI Tool calling
Ranked by SWE-Bench Verified
Mistral AI: Mistral Medium 3.5 T
Reasoning Tools JSON Open weights 77.6

Balanced Mistral model for enterprise assistants, multilingual work, and tools

mistral/mistral-medium-2604 2026-04-29 262.144K context $1.5/M input $7.5/M output
9 providers
Mistral AI: Mistral Medium (latest) T
Tools JSON Open weights 77.6

Balanced Mistral model for enterprise assistants, multilingual work, and tools

mistral/mistral-medium-latest 2026-04-29 262.144K context $1.5/M input $7.5/M output
5 providers
Mistral AI: Devstral Medium T
Tools 61.6

Mistral coding agent model for repository tasks and software engineering workflows

mistral/devstral-medium-2507 2025-07-10 128K context $0.4/M input $2/M output
2 providers
Mistral AI: Devstral Small T
Tools Open weights 53.6

Mistral coding agent model for repository tasks and software engineering workflows

mistral/devstral-small-2507 2025-07-10 128K context $0.1/M input $0.3/M output
3 providers