Main results of the NeurIPS 2026 paper (Figure 3): 18 agent / backbone configurations on the 76 BioXArena tasks across 9 domains. Click a task name for its description, or a score for the details of that run.
Every task is scored by the official evaluator and normalized to 0–1; a task without a valid score (timeout, no or invalid submission, agent failure) counts as 0, and any run longer than 2 h (7,200 s) is a failure even if a submission was written. Successful: tasks (out of 76) whose submission passed the task grader. Task Avg: mean normalized score over all 76 tasks, with failed tasks scored 0 (used for the ranking). Domain Avg: mean of the 9 domain means. Success-only Avg: mean score over the successful tasks only.