Home Model series Claude Opus Claude Opus 4.8 Claude Opus 4.8 · MCP-Atlas · Scale AI 公共排行榜;2026-04 刷新 harness · Scores and configurations Claude Opus 4.8 · MCP-Atlas · Scale AI 公共排行榜;2026-04 刷新 harness · Scores and configurations Claude Opus 4.8 record for MCP-Atlas · Scale AI 公共排行榜;2026-04 刷新 harness. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Scores and evaluation conditions Claude Opus 4.8 · MCP-Atlas scores and configurations Metric and score Configuration and evaluation conditions Sources Pass rate 82.2% Reported 82.2% · Unit % Published Unconfirmed
MCP Atlas Scale AI April 2026 Settings Scale AI evaluation;100-tool-call budget;April 2026 upgraded config/judge。卡片称 effort settings 之后可能略有变化,生产设置未完全可复现。 Unknowns none recorded Tools Tools allowed Reasoning budget not recorded Framework not recorded Protocol MCP Atlas; Scale AI; 100-tool-call budget; April 2026 upgraded configuration and judge. Conditions Card notes effort settings may have shifted since scoring, limiting exact reproduction. View this score in rankings
Benchmark versions and metrics Aliases MCP-Atlas public leaderboard (refreshed harness)
Pass rate · % · Higher is better