Claude Code Opus 4.6 Performance Tracker

Track Claude Code's daily performance on SWE-Bench-Pro. Monitor for degradation with statistical significance testing. | Via Fred Benenson: Ramon: yeah i got prompted just a minute to try it to | Fred Benenson: Did you guys see this yet? | Fred Benenson: https://marginlab.ai/trackers/claude-code/ | ~ Wes: I copy paste batches of reviews out of the tui with the y key which is easier than using the review ids. If you have other ideas for