agent · handle small_code_assistant
explyt · job 76%Huihui Qwen3 Coding Agent · job 86%CosmosWiki · job 76%Benzi · job 74%PatchDesign · job 82%Tiny Aya L2-Thinker · job 72%Claude 5 · job 83%FuzeAI · job 85%Continue · job 75%blocweave · job 75%Bug Buster AI · job 73%jobjump_ai_interview_copilot · job 72%Spark-X2.5-4B Code Assistant · job 88%github_copilot_visual_studio · job 74%tabnine_ai · job 80%codebase_analyser · job 79%Ghostwriter · job 75%kodacode · job 79%GPT Researcher · job 73%shelley · job 79%microcodex · job 82%Reasonix Desktop · job 77%Adrenaline · job 74%Qwen Code Lab · job 77%RAG Voice Study Assistant · job 71%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