agent · handle spark_x25_4b_code · source page
github_copilot_visual_studio · job 75%coding_agent · job 77%PatchDesign · job 84%command_code · job 77%Huihui Qwen3 Coding Agent · job 82%Cursor · job 79%pikoclaw · job 72%Codex · job 79%tabnine_ai · job 79%blocweave · job 73%Small Code Assistant · job 88%Benzi · job 75%CosmosWiki · job 73%Adrenaline · job 72%FuzeAI · job 87%explyt · job 75%shelley · job 80%Reasonix Desktop · job 78%minicode_agent · job 71%kodacode · job 79%codebase_analyser · job 70%Ghostwriter · job 77%Claude 5 · job 81%Continue · job 77%Code Agent · job 74%AbstractCode · job 80%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series