Poolside launches Laguna S 2.1, a 118B MoE coding model that leads its weight class on long-horizon benchmarks

Laguna S 2.1

Poolside released Laguna S 2.1 today, a 118B MoE model with 8B active parameters per token and a 1M-token context window. It scores 70.2% on Terminal-Bench 2.1, beating DeepSeek-V4-Pro Max (64.0%) and Inkling (63.8%), and trailing Tencent Hy3 (295B) by only 1.5 points. On DeepSWE long-horizon tasks it hits 40.4% vs DeepSeek-V4-Pro Max's 9.0%. Poolside says training to launch took under nine weeks and published full eval trajectories. The post doesn't disclose training data cutoff or non-coding performance.

Why it matters: Poolside ships a small-activation MoE coding model that beats DeepSeek-V4-Pro Max on Terminal-Bench 2.1 (70.2% vs 64.0%) with a 1M context window. Capped below 85 because Poolside lacks tier-1 market presence and third-party repro — treat as a strong product update with number...