agent_system

DeepSeek-V4 Pro [high] swe-rebench:DeepSeek-V4 Pro [high]__tools

config_cd306ea55772d6cddc152bf079e0a2caf9ad5196e75005290fb2ccf874735648

Published ranking

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

40%

capability score

Rank

14

Evidence families

1

Claim

Outside top set

Uncertainty was not reported

Configuration passport

Canonical name
DeepSeek-V4 Pro [high]
Revision
swe-rebench:DeepSeek-V4 Pro [high]__tools
Interaction policy
agentic
Passport class
agent-system-v1
Harness
swe-rebench-tools
Scaffold
DeepSeek-V4 Pro [high]__tools

Source evidence

Publication snapshotexplorer_58c2cf3a940443b4e1fdfd119dc7ce463191fe444e5acaf18aeac03b2b5cb982

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