Poolside just released Laguna S It's a 118B total parameter Mixture-of-Experts model with 8B activated per token, a context window of up to 1M tokens, and thinking and no-thinking modes. On Terminal-Bench 2.1 it scores 70.2, sitting beside models 5–25x its size and ahead of several of them. And on DeepSWE, the hardest long-horizon benchmark we ran, Laguna S 2.1 scores 40.4, outperforming some open models with more than 1T parameters. For every score we publish today, we're releasing the full trajectory of every trial in the final evaluation set at http://trajectories.poolside.ai Laguna S 2.1 is available on Hugging Face from day one under OpenMDW-1.1, with BF16, FP8, INT4 and NVFP4 weights, official GGUF and MLX conversions, and official DFlash draft models. Would love to hear how people use in OpenHands and the aspects that work well/not so well for you 🫶 poolside.ai/blog/introducing-laguna-s-2-1