List your company

Program Repair on SpreadsheetBench (test)

84Pass RateIG
39.2850.8962.574.11May 20, 2026

Evaluation results

MethodLinks
IGRound=A4, Patcher Model=Claude Code (Claude Opus 4.6)2026.0584
RLMRound=A3, Patcher Model=Claude Code (Claude Opus 4.6)2026.0584
IGRound=A2, Patcher Model=Claude Code (Claude Opus 4.6)2026.0581
RLMRound=A2, Patcher Model=Claude Code (Claude Opus 4.6)2026.0581
CC SubagentsRound=A3, Patcher Model=Claude Code (Claude Opus 4.6)2026.0581
IGRound=A3, Patcher Model=Claude Code (Claude Opus 4.6)2026.0580
IGRound=A5, Patcher Model=Claude Code (Claude Opus 4.6)2026.0580
Pure PatcherRound=A1, Patcher Model=Claude Code (Claude Opus 4.6)2026.0580
RLMRound=A1, Patcher Model=Claude Code (Claude Opus 4.6)2026.0579
IGRound=A1, Patcher Model=Claude Code (Claude Opus 4.6)2026.0577
CC SubagentsRound=A1, Patcher Model=Claude Code (Claude Opus 4.6)2026.0576
CC SubagentsRound=A2, Patcher Model=Claude Code (Claude Opus 4.6)2026.0571
Pure PatcherRound=A2, Patcher Model=Claude Code (Claude Opus 4.6)2026.0558
Pure PatcherRound=A3, Patcher Model=Claude Code (Claude Opus 4.6)2026.0558
CC SubagentsRound=A0, Patcher Model=Claude Code (Claude Opus 4.6)2026.0544
RLMRound=A0, Patcher Model=Claude Code (Claude Opus 4.6)2026.0542
IGRound=A0, Patcher Model=Claude Code (Claude Opus 4.6)2026.0541
Pure PatcherRound=A0, Patcher Model=Claude Code (Claude Opus 4.6)2026.0541