Launching today
Tura
80% fewer tokens; 16.7 percentage points higher success.
9 followers
80% fewer tokens; 16.7 percentage points higher success.
9 followers
Across 348 long-horizon benchmark sessions, Tura used up to 80% fewer tokens on the rewrite benchmark and improved the DeepSWE pass rate by up to 16.7 percentage points compared with Codex CLI.
honestly the token savings caught me off guard, ran it on a gnarly refactor and it just chewed through way less than I'd expect for the quality it spit out
@yeliz957285 Thank you. You can try some e2e frontend and full-stack tasks; normally, the diff is much larger than with refactoring.
Love that you're showing real benchmark numbers instead of vague promises. One thing I'd want to see: a way to compare token costs side-by-side against Codex or Cursor in the same session. A built-in cost diff readout would make it way easier to justify switching.
Saw the token savings on long rewrites and figured it was too good to be true, but the numbers held up in my own tests. Genuinely impressed by how much faster it gets through big refactors without losing track.
the jump on DeepSWE without bloating token usage is genuinely impressive, most tools trade one for the other
@ecekikardeyzsa I'm fixing some timeout issues and will submit the full benchmark next week to deepswe.