dottxt Tool-Call Index: Worst Provider Breaks 19x More Tool Calls Than Best

remilouf · x · 2026-11-20

dottxt launched a Tool-call Index showing the provider matters as much as the model: on the same model, the worst inference provider breaks up to 19x more tool calls than the best (e.g. gpt-oss-120b ranges from 0.01% to 71.96% broken calls). The index tracks 64 models across 66 providers, updates weekly, and ships a choose-provider skill so your agent can pick the provider itself: npx skills add https://providers.dottxt.ai --skill choose-provider.

Related event: dottxt Tool-call Index: Worst Providers Show 19x More Broken Tool Calls(3 posts)→

Original post →

More from coding & agent

coding & agent channel →