A tiny 118B open model just outscored DeepSeek's 1.6-trillion-parameter giant at coding (poolside.ai)
On Terminal-Bench 2.1, Laguna S 2.1 scores 70.2%, ahead of DeepSeek-V4-Pro-Max's 64% at roughly a fourteenth of the parameter count. Poolside built it in under nine weeks and prices it at 10 cents per million input tokens on OpenRouter, weights open in BF16, FP8, INT4, and GGUF.
The catch surfaced on Hacker News fast: several deployment recipes ship with "thinking" switched off by default, and without it the numbers don't reproduce locally — one tester said the model looked mediocre until he forced the flag on himself.
Sign in to save