Laguna S 2.1

Summary

Today we’re releasing Laguna S 2.1, a significant step forward in our development of models that pursue longer horizon work and make effective use of reasoning.Laguna S 2.1 is a 118B total parameter Mixture-of-Experts model with 8B activated parameters per token and supports a context window of up to 1M tokens in thinking and no-thinking modes. It went from the start of training to launch in under nine weeks, and on long-horizon coding benchmarks it holds its own against models many times its size. For every benchmark score we publish today, we are releasing full trajectories for every trial in the final evaluation set at trajectories.poolside.ai. Laguna S 2.1 118B-A8B Tencent Hy3 295B-A21B Inkling 975B-A41B Nemotron 3 Ultra 550B-A55B DeepSeek-V4-Pro Max 1.6T-A49B Kimi K3 2.8T-A50B Qwen 3.7 Max — Muse Spark 1.1 — Claude Fable 5 — Terminal-Bench 2.1 Resolved tasks on Terminal-Bench 2.1. SWE-Bench Multilingual Resolved tasks on SWE-Bench Multilingual. SWE-Bench Pro (Public Dataset) Resolved tasks on SWE-Bench Pro (Public Dataset). DeepSWE Resolved tasks on DeepSWE. SWE Atlas (Codebase QnA) Resolved tasks on SWE Atlas (Codebase QnA). Toolathlon Verified Resolved tasks on Toolathlon Verified. Benchmarks as of 21 July 2026. pass@1 averaged over 4 attempts per task, except DeepSWE, SWE Atlas (Codebase QnA) and Toolathlon Verified that had 3 attempts per task. For all benchmarks we take the maximum of the vendor self-reported score, benchmark author leaderboard or third-party leaderboard (Artificial Analysis), except SWE Atlas (Codebase QnA) where we do not use third-party leaderboard figures.Punching above its weight classLaguna S 2.1 is, as far as we can measure, the most capable agentic coding model in its weight class by a wide margin.S 2.1 scores 70.2% on Terminal-Bench 2.1 in our agent harness with thinking enabled. Its compact size makes it uniquely suitable for complex work on local machines. Benchmark Terminal-Bench 2.1SWE-Bench MultilingualSWE-Bench Pro (Public D...