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.
Reported score
Tools allowed / max · Output limit 163840 tokens / Framework not recorded · Full set; w/ Tools; temperature=1.0; top_p=0.95; maximum generation length=163,840; maximum context=300,000 with context management; GPT-5.6-luna (medium) judge; default reasoning_effort=max.
HLE w/ Tools · GLM-5.3-Flash模型卡;full set; w/ Tools · Reported score · Tools allowed / max · Output limit 163840 tokens / Framework not recorded · Full set; w/ Tools; temperature=1.0; top_p=0.95; maximum generation length=163,840; maximum context=300,000 with context management; GPT-5.6-luna (medium) judge; default reasoning_effort=max.