GripProbe Run Summary

ShellModelBackendHashFormatTestStatusReasonTrajectoryInvokedMatchWarmup (s)Measured (s)Details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolJSON Rank From FilePASSrecoveredyes100%48.66568.657details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolPatch File From Prepared PatchFAILcleanyes0%9.5339.284details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolPython File QuotedPASSrecoveredyes100%19.50717.0details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolPython File Quoted DEFAILcleanno0%22.3592.369details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolPython File Quoted RUPASSrecoveredyes100%17.017.85details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolSave FilePASSrecoveredyes100%16.79916.55details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolShell Date DEPASSrecoveredyes100%19.15519.804details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolShell Date RUPASSrecoveredyes100%18.60218.352details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolShell FilePASSrecoveredyes100%17.35117.201details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolWeb Fetch JSON RawPASSrecoveredyes100%36.7942.548details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolWeb Nonce ProofTIMEOUTcleanyes0%2.168120.009details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolWeb Search JSON RankedTIMEOUTcleanyes0%93.659120.006details
gptmelocal/cryptidbleh/gemma4-claude-opus-4.6:latestollama0961fd31e5ae57fe3f7bba84ec4dbda92fbd90c1151b31e002864a423e297cf4toolWeekly Plan Next WeekFAILrecoveredyes0%15.54723.967details