agent_system

DeepSeek V4.1 Flash macroscopebench:high-effort

config_2b2e93dfccd56f89985469205995a700afa68ca234cb33876dd8bebc4d1b4b49

Published ranking

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

66%

capability score

Rank

27

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
DeepSeek V4.1 Flash
Revision
macroscopebench:high-effort
Interaction policy
agentic
Passport class
agent-system-v1
Harness
macroscope-code-review
Scaffold
macroscope-code-review

Source evidence

Publication snapshotexplorer_4a8c9a49ef7bff07108192a8cc1f24cdf9deb46d839585dcde823de67b156e77

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