DeepCoder
DeepCoder is a fully open source code-reasoning and generation model released by Agentica Project in collaboration with Together AI. It is fine-tuned from DeepSeek-R1-Distilled-Qwen-14B using distributed reinforcement learning, achieving a 60.6% accuracy on LiveCodeBench (representing an 8% improvement over the base), a performance level that matches that of proprietary models such as o3-mini (2025-01-031 Low) and o1 while using only 14 billion parameters. It was trained over 2.5 weeks on 32 H100 GPUs with a curated dataset of roughly 24,000 coding problems drawn from verified sources (including TACO-Verified, PrimeIntellect SYNTHETIC-1, and LiveCodeBench submissions), each problem requiring a verifiable solution and at least five unit tests to ensure reliability for RL training. To handle long-range context, DeepCoder employs techniques such as iterative context lengthening and overlong filtering.
Learn more
DeepSWE
DeepSWE is a fully open source, state-of-the-art coding agent built on top of the Qwen3-32B foundation model and trained exclusively via reinforcement learning (RL), without supervised finetuning or distillation from proprietary models. It is developed using rLLM, Agentica’s open source RL framework for language agents. DeepSWE operates as an agent; it interacts with a simulated development environment (via the R2E-Gym environment) using a suite of tools (file editor, search, shell-execution, submit/finish), enabling it to navigate codebases, edit multiple files, compile/run tests, and iteratively produce patches or complete engineering tasks. DeepSWE exhibits emergent behaviors beyond simple code generation; when presented with bugs or feature requests, the agent reasons about edge cases, seeks existing tests in the repository, proposes patches, writes extra tests for regressions, and dynamically adjusts its “thinking” effort.
Learn more
Devstral Small 2
Devstral Small 2 is the compact, 24 billion-parameter variant of the new coding-focused model family from Mistral AI, released under the permissive Apache 2.0 license to enable both local deployment and API use. Alongside its larger sibling (Devstral 2), this model brings “agentic coding” capabilities to environments with modest compute: it supports a large 256K-token context window, enabling it to understand and make changes across entire codebases. On the standard code-generation benchmark (SWE-Bench Verified), Devstral Small 2 scores around 68.0%, placing it among open-weight models many times its size. Because of its reduced size and efficient design, Devstral Small 2 can run on a single GPU or even CPU-only setups, making it practical for developers, small teams, or hobbyists without access to data-center hardware. Despite its compact footprint, Devstral Small 2 retains key capabilities of larger models; it can reason across multiple files and track dependencies.
Learn more
Laguna M.1
Laguna M.1 is Poolside’s most capable model for agentic coding, built and trained in-house for software development workflows. It is a 225B total-parameter Mixture of Experts model with 23B activated parameters, trained completely in-house on 30T tokens using 6,144 interconnected NVIDIA H200 GPUs. Poolside trained Laguna M.1 from scratch with its own data work, training codebase, and async on-policy reinforcement learning in its agent harness, all with agentic coding in mind. The model is designed to perform at its best inside Poolside’s coding agent, where it can reason through software tasks, interact with tools, edit code, run tests, and support longer autonomous development sessions. Laguna M.1 is built for developers and teams working on complex coding tasks that require stronger reasoning, architectural understanding, terminal use, and multi-step execution than lightweight models can provide.
Learn more
