Shared benchmark
neondatabase/neon · created Jul 24, 2026 · 16 / 100 tasks
Tasks
Runs
latest run in progress — follow it live →
| Status | Models | Tasks | Judge | Started | Duration |
|---|---|---|---|---|---|
| running | claude-opus-4-8, claude-opus-5, gemini-3-flash, claude-sonnet-4 | 16 | claude-opus-4-8 15/16·claude-opus-5 11/15·gemini-3-flash 7/16 |
Powered by YourCodingBench — benchmark coding models on your own repo's merged PRs. sign in
| Jul 24, 19:05 |
| … |