OSS
Bullet Claims 95.8% on SWE-bench Verified at 119 Seconds Per Task and Lands Fifth on Product Hunt
Bullet launched on Product Hunt with 224 upvotes, positioning explicitly as '30-60% faster than Claude Code and Codex.' It claims 95.8% on SWE-bench Verified at 119s/task, achieved by auto-selecting model and reasoning level per prompt, parallelizing searches/reads/commands, and using targeted code search rather than embedding the whole repo. It runs against your existing Claude Code or Codex subscription, your own API keys, or an on-device model. Built by Yale CS grads with ex-AppLovin/Citadel backgrounds. The benchmark is self-reported and unverified by a third party, which is the obvious caveat.
Source
↳ Follow the thread