Ante
anteAnte's pass rate on every board it ran on. Scores on different boards don't add up, so this page doesn't add them.
On each board
Terminal-Bench 2.0
Every board here: version not recorded, full, 89 tasks, 5 attempts, openRanks 1–2
2 harnesses64.7%56.2–72.1Ante minus sageagent: −0.4 points, 95% interval −6.7 to +5.4, over 89 tasks both ran; too close to call.
2 harnesses64.7%56.2–72.1Ante minus sageagent: −0.4 points, 95% interval −6.7 to +5.4, over 89 tasks both ran; too close to call.
Rank 2
3 harnesses73.7%66.3–80.2Ante minus tongagents 0.8.0: −6.5 points, 95% interval −12.4 to −1.3, over 89 tasks both ran; a clear difference.
3 harnesses73.7%66.3–80.2Ante minus tongagents 0.8.0: −6.5 points, 95% interval −12.4 to −1.3, over 89 tasks both ran; a clear difference.