Poolside releases Laguna M.1: 225B parameter MoE model scores 74.6% on SWE-bench Verified
Poolside has released Laguna M.1, a 225B total parameter Mixture-of-Experts model with 23B activated parameters per token, designed for agentic coding tasks. The model scores 74.6% on SWE-bench Verified and 63.1% on SWE-bench Multilingual, released under Apache 2.0 license.
Laguna M.1 at a glance
How Laguna M.1 ranks now
| Benchmark | Score | Rank | Source |
|---|---|---|---|
| SWE-bench Verified | 74.6% | 40 of 80 | Hugging Face model card, Jun 2026 ↗ |
Rank is against every model in our database with a sourced score on that benchmark, each counted once with its best score.
Poolside Releases Laguna M.1: 225B Parameter MoE for Agentic Coding
Poolside has released Laguna M.1, a 225B total parameter Mixture-of-Experts (MoE) model with 23B activated parameters per token, designed specifically for agentic coding and long-horizon development work.
Architecture and Specifications
Laguna M.1 uses a 70-layer MoE transformer with 256 experts and top-k=16 routing. The first 3 layers are dense SwiGLU, while the remaining 67 layers use sparse MoE. The model employs global attention across all layers with 64 Q-heads, 8 KV-heads, and head dimension 128. Context window extends to 262,144 tokens.
The model uses RoPE with YaRN for positional encoding and includes native reasoning support through interleaved thinking between tool calls. Training involved pre-training, post-training, and reinforcement learning stages using the Muon optimizer.
Benchmark Performance
Poolside reports the following scores on agentic coding benchmarks (averaged over 4 runs at temperature=1.0, top_k=20):
- SWE-bench Verified: 74.6%
- SWE-bench Multilingual: 63.1%
- SWE-bench Pro: 49.2%
- Terminal-Bench 2.0: 45.8%
For comparison, DeepSeek-V4 Flash (284B total, 13B active) scores 79.0% on SWE-bench Verified, while Qwen3.5 (397B total, 17B active) achieves 76.2%. Claude Sonnet 4.6 scored 79.6% on SWE-bench Verified and 59.1% on Terminal-Bench 2.0, according to Poolside's comparison table.
Deployment and Availability
The model is released under Apache 2.0 license and supports deployment via vLLM (version 0.21.0+), SGLang, Transformers (v5.7.0+), and TensorRT-LLM. Quantized checkpoints are available in FP8 and NVFP4 formats.
Poolside provides a terminal-based coding agent called "pool" that integrates with the model and supports the Agent Client Protocol. The tool auto-configures with Zed and JetBrains editors.
All benchmarking used Poolside's pool agent harness with maximum 500 steps and sandboxed execution. Tasks ran in 8GB RAM/2 CPU sandboxes, except Terminal-Bench 2.0 which used 48GB RAM/32 CPUs. Poolside states they ran a reward-hack judge post-hoc and "did not find significant reward hacking."
What This Means
Laguna M.1 represents a competitive open-weight option for agentic coding tasks, though it trails frontier models like DeepSeek-V4 Flash on SWE-bench benchmarks by 4-11 percentage points depending on the task. The Apache 2.0 license and support for standard serving frameworks lower deployment barriers compared to proprietary alternatives. The 225B total parameter count with 23B active parameters positions it between smaller dense models and larger MoE architectures in terms of inference cost, though actual performance-per-dollar will depend on hardware and optimization.
Related Articles
Zyphra releases ZONOS3-Mini, an Apache 2.0 TTS model with 100M active parameters
Zyphra released ZONOS3-Mini, an Apache 2.0 text-to-speech model with 800M total parameters and 100M active parameters. It clones voices, steers delivery word by word and runs in real time in the browser.
Ant Group's Robbyant open-sources LingBot-Touch, a tactile model trained on nearly 5,000 hours of data
Robbyant, the embodied-AI company under Ant Group, has open-sourced LingBot-Touch under Apache-2.0. The tactile foundation model was pretrained on nearly 5,000 hours of real data and covers magnetic, visuotactile and piezoresistive sensors. Tiny and Small checkpoints are on Hugging Face and ModelScope.
MBZUAI's IFM releases PAN 2, an Apache 2.0 world model with a 29B diffusion transformer
The Institute of Foundation Models (IFM) at MBZUAI released PAN 2, an Apache 2.0 world model. It couples an LLM planner with a 29B diffusion transformer to simulate up to 20 seconds of action outcomes as video.
Fish Audio releases Live 3, a full-duplex voice model that reacts in as little as 186 ms
Fish Audio released Live 3, a full-duplex voice model for voice agents. It listens while it speaks, separates "mm-hmm" from real interruptions, and can react in as little as 186 ms. It is English only at launch.
Comments
Loading...