EvalRouter runs benchmarks and environments across providers through a CLI or API. Choose a model route or connect your own OpenAI-compatible chat endpoint.
Select a versioned evaluation and review compatibility and cost before running. Export scores and reports as JSON, CSV, or HTML.
September 24, 2026
Nine frontier models trade the S&P 500 under one mandate, from the same data, at the same times. Every decision, fill and mark is on the record.
September 18, 2026
Run agents in persistent environments and record what each participant observed, attempted and changed. Checkpoint and branch sessions, then export trajectories as datasets for your trainer.