OpenRouter model
Mistral: Devstral 2 2512
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
- Provider
- OpenRouter
- Availability
- Available
- Model ID
- mistralai/devstral-2512
- Snapshot
- 2026-10-07
Mistral: Devstral 2 2512 Benchmarks & Agentic Accuracy
Verified primary research & developer preference metrics
What This Means in Real Software Development
- 59.2% on SWE-bench Verified, demonstrating deep repository-level debugging ability.
- Tuned specifically for tool calling, shell command execution, and test assertion verification.
- 71.5% on AIME confirms strong logical deduction for edge-case reasoning.
- Priced at $0.50/M input, offering an exceptional balance of price and autonomous capability.
Swarm Multi-Agent Topology
Best Paired With: Claude 3.7 Sonnet as Lead Planner
High-accuracy code synthesis specifically tuned for autonomous test loops and multi-file patches.
Executes isolated feature work inside dedicated worktrees with full Git isolation.
What Developers & Practitioners Are Saying
Real-world field observations, production strengths, and developer consensus
"Mistral's agentic engineering model, offering enhanced tool calling and automated bug fixing capabilities."
Verified Real-World Strengths
- 59.2% on SWE-bench Verified
- Strong compliance with unified diff and git patch conventions
- Reliable tool execution without syntax errors
Production Caveats & Gaps
- Trails Claude 3.7 Sonnet on complex distributed systems reasoning
Primary Sources & Methodology Citations
- Devstral 2512: Autonomous Software Engineering Model — Mistral AI (December 2025)
Head-to-Head Frontier Comparisons: Mistral: Devstral 2 2512 vs Rivals
Standardized, side-by-side benchmark & economics comparison against peer models
| Model | Role / Tier | SWE-bench | LiveCodeBench | LMSYS Elo | AIME | Input / Output |
|---|---|---|---|---|---|---|
Mistral: Devstral 2 2512OpenRouterCurrent | Tier 2: Dedicated Autonomous Coder | 59.2% | 54% | 1360 | 71.5% | $0.5 / $1.5 |
Llama 4 MaverickMeta Compare Mistral: Devstral 2 2512 vs Llama 4 Maverick → | Tier 2: Next-Gen Open Frontier Engine | 61.2% | 55.4% | 1370 | 78.5% | $0.8 / $2.4 |
OpenAI o4-miniOpenAI Compare Mistral: Devstral 2 2512 vs OpenAI o4-mini → | Tier 2: High-Speed Deductive Engine | 56.8% | 73.4% | 1385 | 90.1% | $1.2 / $4.8 |
DeepSeek R1DeepSeek Compare Mistral: Devstral 2 2512 vs DeepSeek R1 → | Tier 2: Deep Algorithmic Specialist | 49.2% | 49.8% | 1360 | 79.8% | $0.55 / $2.19 |
Mistral Medium 3.5Mistral Compare Mistral: Devstral 2 2512 vs Mistral Medium 3.5 → | Tier 3: European Sovereign Subagent | 45% | 38% | 1250 | — | $0.2 / $0.8 |
Mistral: Devstral 2 2512 model overview
Mistral: Devstral 2 2512 is listed in the public Swarm catalog through OpenRouter. This page summarizes the verified catalog fields used by Swarm without claiming real-time access for every provider account.
- Provider
- OpenRouter
- Family
- OpenRouter
- Context window
- 262.1K tokens
- Thinking support
- Not supported
- Availability status
- Available
- Catalog ID
- openrouter/mistralai/devstral-2512
Run Mistral: Devstral 2 2512 in Swarm
Verified CLI workflow & multi-agent architecture
swarm ctl model set --provider openrouter --model openrouter/mistralai/devstral-2512# Or switch interactively inside the terminal TUI:
/modelsSubagent Role Matrix
Assign Mistral: Devstral 2 2512 to specialized system roles in ~/.swarm/config.json:
- Primary / Planner: Orchestrates full task DAGs and multi-stage pipelines.
- Coder Subagent: Generates code and unit tests inside private Git worktrees.
- Finder Subagent: Performs read-only code search, symbol discovery, and mapping.
Public catalog snapshot. Catalog availability is not a real-time provider status or an access guarantee.