Stripe open-sources evals benchmarking how well coding agents build real integrations
emilygsands · x · 2026-11-20
Stripe open-sourced Stripe evals, a benchmark measuring how well coding agents build high-quality Stripe integrations, plus the first leaderboard.
- 69 scenarios across one-time payments, subscriptions, and Connect, run on 14 model-harness pairs, with and without the Stripe agent plugin
- Tasks include hosted checkout, metered billing, per-seat subscriptions, and marketplace payment splitting, driven by a roleplaying agent
- The plugin lifts every pair by 3-8 points; web searches drop 96% as agents lean on trusted guidance
- One-time payments: gpt-6-astra hits 90→96 with the plugin; subscriptions remain hardest (top 83)
- Results will be updated periodically as new models ship
Related event: Stripe Open-Sources Agent Evals: Only 29% of Coding Agents Fully Pass(5 posts)→
More from coding & agent
- Stripe launches coding-agent evals: agents meet all criteria in only 29% of runs — hazelcough · 2026-11-20
- Google's Antigravity in beta for 2 years still can't handle remote file uploads — jasondeanlee · 2026-11-20
- Firecrawl launches Grok Bot plugin with 3,300+ data tools, claims 21% answer quality lift — devdigest · 2026-11-20
- OnchainBench launches: benchmarking whether crypto AI agents can be trusted with your keys — DavideCrapis · 2026-11-20
- Stripe open-sources coding-agent evals: 69 scenarios, agents fully pass only 29% of runs — emilygsands · 2026-11-20
- Fig previews RoleCUA: 780+ hours of expert work to train agents for month-long job functions — adityaag · 2026-11-20