Which AI model to use for coding by task, budget, speed and context: the top 3 with their estimated cost per task, from La Rebelión’s own benchmark and the catalogue of Rebel Router, the open AI model router that cuts the cost of Claude Code and OpenCode.
Model Recommender
Pick the kind of task and your limits: we return the three models that fit best, with their estimated cost per task and why.
Quality: pass rate in our benchmark when the model was measured, otherwise the Rebel Router catalogue score. Cost: measured, or estimated from official prices for a typical task.
Cost and pass rate of each model
Our benchmark: the same set of real tasks run with every model through Rebel Router. Updated daily.
Cost per task against pass rate
Loading data…
Pass rate by task class (mean across models)
Loading data…
Savings from automatic routing
Loading data…
Intelligence index: top 12
Loading data…
How it works
The data is refreshed daily: the Rebel Router catalogue (official prices per million tokens, context and speed), our benchmark of real tasks (refactors, tests, bugs, documentation) and the Artificial Analysis index.
The recommender filters by context, budget and open models, then ranks by measured quality for that kind of task, cost and speed. Same data, same answer: no AI in the loop.
AI for developers: guides and labs
The lab and the article behind the recommender, and the blog’s latest guides and explainers.
- Build your own AI model router with Rebel Router
- Why you should stop using one model for everything: an AI model router