Extended thinking off; 200K context and default sampling are stated for MCP Atlas; Table 2.3.A applies its no-thinking footnote to MCP Atlas, τ² Retail and τ² Telecom.
未知项
The system card does not state an independent effort level for these no-thinking evaluations.
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
MCP Atlas;主表未说明题集/调用预算。
条件
No extended thinking; 200K context; default temperature/top_p; 5-trial average per Table 2.3.A.
Multi-step MCP workflows on production-like servers; the card reports 85.8% pass rate and 89.1% mean claim coverage, and warns that effort settings may since have changed.
未知项
Effort and run count are not stated; the score may not be precisely reproducible.
工具
允许工具
推理预算
未记录
框架
未记录
协议
MCP-Atlas; multi-step MCP workflows.
条件
Reported effort may have changed since evaluation; the card says the score may not be precisely reproducible.
Multi-step MCP workflows on production-like servers; the card reports 85.8% pass rate and 89.1% mean claim coverage, and warns that effort settings may since have changed.
未知项
Effort and run count are not stated; the score may not be precisely reproducible.
工具
允许工具
推理预算
未记录
框架
未记录
协议
MCP-Atlas; mean claim coverage.
条件
Reported effort may have changed since evaluation; the card says the score may not be precisely reproducible.
Differences are calculated only for unique, active, exact values between direct predecessors when the unit, metric, and explicitly recorded configuration and conditions match.
· 1 score record for this release, including 1 exact value (may include historical records)
Claude Opus 4.5 · MCP-Atlas scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Score62.3%Reported 62.3% · Unit %
Published Unconfirmed
No extended thinking
Settings
Extended thinking off; 200K context and default sampling are stated for MCP Atlas; Table 2.3.A applies its no-thinking footnote to MCP Atlas, τ² Retail and τ² Telecom.
Unknowns
The system card does not state an independent effort level for these no-thinking evaluations.
Tools
Tool access not recorded
Reasoning budget
not recorded
Framework
not recorded
Protocol
MCP Atlas;主表未说明题集/调用预算。
Conditions
No extended thinking; 200K context; default temperature/top_p; 5-trial average per Table 2.3.A.
· 2 score records for this release, including 2 exact values (may include historical records)
Claude Opus 5 · MCP-Atlas scores and configurations
Metric and score
Configuration and evaluation conditions
Sources
Pass rate85.8%Reported 85.8% · Unit %
Published Unconfirmed
MCP-Atlas · reported production evaluation
Settings
Multi-step MCP workflows on production-like servers; the card reports 85.8% pass rate and 89.1% mean claim coverage, and warns that effort settings may since have changed.
Unknowns
Effort and run count are not stated; the score may not be precisely reproducible.
Tools
Tools allowed
Reasoning budget
not recorded
Framework
not recorded
Protocol
MCP-Atlas; multi-step MCP workflows.
Conditions
Reported effort may have changed since evaluation; the card says the score may not be precisely reproducible.
Multi-step MCP workflows on production-like servers; the card reports 85.8% pass rate and 89.1% mean claim coverage, and warns that effort settings may since have changed.
Unknowns
Effort and run count are not stated; the score may not be precisely reproducible.
Tools
Tools allowed
Reasoning budget
not recorded
Framework
not recorded
Protocol
MCP-Atlas; mean claim coverage.
Conditions
Reported effort may have changed since evaluation; the card says the score may not be precisely reproducible.