benchmark 12

OMK — Observe. Measure. Know. Evidence-backed knowledge changes for AI applications.

Talk to Excel in DeepSeek Harness: read, edit, clean and report on spreadsheets by conversation. Re-checks every formula after each edit, repairs silent errors, and needs no local Excel for the core work (charts and PDF export use Windows Excel).

虚拟 DSH 环境跑分机 — 插件/Skill 加载与工具调用基准（L1 零 token）。dsh-plugin-hub 生态的可扩展类插件：为 hub 提供独立性能评分（加载/工具调用各环节耗时）。

Agent evaluation platform: benchmark YAML, headless run orchestration, trace-based metrics, and run reports

Controlled A/B comparisons and evidence-backed reports for DeepSeek Harness plugins and presets.

Play Minecraft from DeepSeek Harness: the agent observes, moves, mines and crafts through tools backed by a live Mineflayer bot

Check which DeepSeek Harness plugins actually loaded, and look up public evaluation boards on trapstreet.run

Jev (TypeSafe System One decision model) for DeepSeek Harness — seven tools: jev_decision (up to 25 typed questions in one parallel call, measured median 266-484 ms), jev_choose (rank 2-10 approaches), jev_batch (one set of up to 5 judgments over 1-20 tex

Run the same prompt through every model you have, and see the difference without squinting.

DSH Agent experiment & A/B comparison — run the same coding task in two isolated workspaces and compare objective metrics (wall time, turns, tokens, diff, evaluator results).

DSH 试金石：给「自改造」补上评测这一环——用一套金标准用例，把改动前 vs 改动后跑一遍、打分、对比，好就留、不好就撤。

DSH web plugin: a LiveBench tab in the Trajectory view (right of 对话/轨迹). Run LiveBench evaluations against every model configured in the DeepSeek Harness — pick provider/model, category, task, release and question range from dropdowns, watch progress, and