We ran 720 browser agent tasks with @nottecore across frontier models. One baseline model produced malformed outputs in ~1 out of every 5 ca…

We ran 720 browser agent tasks with @nottecore across frontier models. One baseline model produced malformed outputs in ~1 out of every 5 calls, leading to retries inside multi-step workflows. Across Kimi K2.5, GLM-5, and MiniMax M2.5 served on Fireworks, retry rates were near zero and latency stayed stable even as tasks extended across multiple steps. Same workload. Same agent loop. Different execution behavior. That gap is what shows up as cost, latency, and reliability divergence in production agent systems. Read the report: https://fireworks.ai/blog/agent-execution-tax

Source: Fireworks AI (X) | 2026-05-20