Regular display scope. Rankings are grouped by metric and evaluation protocol. Recorded tool access, budgets, and frameworks are shown separately. Scores remain available for reference when conditions are unspecified.
Accuracy %
Tool access not recorded / xhigh / Framework not recorded · OpenAI MRCR v2, 8 needles, 64K–128K average context; accuracy.
MRCR-V2 · 8-needle; up to 128K average context · Accuracy · Tool access not recorded / xhigh / Framework not recorded · OpenAI MRCR v2, 8 needles, 64K–128K average context; accuracy.
Tool access not recorded / high / Framework not recorded · 8-needle; 128K average/cumulative score.
MRCR-V2 · 8-needle; up to 128K average context · Accuracy · Tool access not recorded / high / Framework not recorded · 8-needle; 128K average/cumulative score.