agent_system

deepseek-v4-pro_none 2026-04-24

config_0ec4386dd9cf763f25ad6463b4a4d9b24d51c2e322a61f5edc47e696326a88f1

Published ranking

This score and claim apply only inside the bound ranking group.

18%

capability score

Rank

40

Evidence families

1

Claim

上位セット圏外

Uncertainty was not reported

Configuration passport

Canonical name
deepseek-v4-pro_none
Revision
2026-04-24
Interaction policy
agentic
Passport class
agent-system-v1
Harness
mini-swe-agent
Scaffold
https://cognition.com/frontiercode

出典エビデンス

Publication snapshotexplorer_58c2cf3a940443b4e1fdfd119dc7ce463191fe444e5acaf18aeac03b2b5cb982

評価方法2026-10-31.1.cost-per-task-wave