No release verdicts yet. Scored jobs show how many tools were tested. The rest are not tested.
Queue
VC1 · Build a landing page from a prompt · Not testedVC2 · Build a full-stack app from a prompt · Not testedVC3 · Deploy and host a vibe-coded app · Not testedVC4 · Add auth and a database to an app · Not testedVC5 · Find security holes in a vibe-coded repo · 1 scoredVC6 · Turn a design or screenshot into UI code · Not testedCA1 · Inline autocomplete and chat in the IDE · Not testedCA2 · Multi-file refactor with an agent · Not testedCA3 · Turn a GitHub issue into a PR autonomously · Not testedCA4 · AI code review on pull requests · Not testedCA5 · Generate unit and end-to-end tests · Not testedCA6 · Run a coding model locally or cheaply · 2 scoredMCP1 · Connect an agent to GitHub · Not testedMCP2 · Let an agent control a browser · Not testedMCP3 · Let an agent query a database · Not testedMCP4 · Give an agent web search and live docs · Not testedMCP5 · Build or host your own MCP server · 3 scoredMCP6 · Find and install MCP servers · Not testedGD1 · Generate 2D sprites and pixel art · Not testedGD2 · Generate 3D models for a game · Not testedGD3 · Make sound effects and music · Not testedGD4 · Voice and dialogue for NPCs · Not testedGD5 · Prototype a playable game from a prompt · Not testedGD6 · Animate characters with AI (mocap/rigging) · Not testedVC1 · Build a landing page from a prompt · Not testedVC2 · Build a full-stack app from a prompt · Not testedVC3 · Deploy and host a vibe-coded app · Not testedVC4 · Add auth and a database to an app · Not testedVC5 · Find security holes in a vibe-coded repo · 1 scoredVC6 · Turn a design or screenshot into UI code · Not testedCA1 · Inline autocomplete and chat in the IDE · Not testedCA2 · Multi-file refactor with an agent · Not testedCA3 · Turn a GitHub issue into a PR autonomously · Not testedCA4 · AI code review on pull requests · Not testedCA5 · Generate unit and end-to-end tests · Not testedCA6 · Run a coding model locally or cheaply · 2 scoredMCP1 · Connect an agent to GitHub · Not testedMCP2 · Let an agent control a browser · Not testedMCP3 · Let an agent query a database · Not testedMCP4 · Give an agent web search and live docs · Not testedMCP5 · Build or host your own MCP server · 3 scoredMCP6 · Find and install MCP servers · Not testedGD1 · Generate 2D sprites and pixel art · Not testedGD2 · Generate 3D models for a game · Not testedGD3 · Make sound effects and music · Not testedGD4 · Voice and dialogue for NPCs · Not testedGD5 · Prototype a playable game from a prompt · Not testedGD6 · Animate characters with AI (mocap/rigging) · Not tested
Run a coding model on a 16GB laptop or via cheap API; complete the CA1 task; record cost/speed.
Job resultWeight 40
32
Speed and effortWeight 15
12
Price and free tierWeight 15
15
Ease of startWeight 10
6
Reliability and trustWeight 10
8
Community signalWeight 10
8
Last tested: 15 Oct 2026. Evidence: Ollama 0.40.4, qwen2.5-coder:3b, 15Gi CPU, no GPU. Two prompts, 65.6s then 44.2s. Final files passed tsc and the debounce/REST checks. Evidence: evidence/2026-10-16/ca6/ollama/.
