agent_system

deepseek-v4-flash mini_swe_agent_deepseek_v4_flash_max

config_ce541a8d1b086c6ec893f0b97904e6a6f35cc3d5f6cef04816ef487c188a8ca1

Published ranking

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

53%

capability score

Rank

47

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
deepseek-v4-flash
Revision
mini_swe_agent_deepseek_v4_flash_max
Interaction policy
agentic
Passport class
agent-system-v1
Harness
mini-swe-agent
Scaffold
mini_swe_agent_deepseek_v4_flash_max

Source evidence

Publication snapshotexplorer_58c2cf3a940443b4e1fdfd119dc7ce463191fe444e5acaf18aeac03b2b5cb982

Methodology2026-10-31.1.cost-per-task-wave