One model. One sentence. One natural world.
Qwen 3.8 Max chose the intermediate steps, placed a crafting table, crafted the target item, and still held it at the end of the recorded run.
Initial first-person capture. The red and blue pixels are a known Prismarine Viewer texture-version caveat, not evidence of placed blocks.
This write-up describes the project state completed on June 30, 2026.
The larger research question is still open. The project has not yet picked a final claim such as action-consequence prediction, social behavior, or model comparison. The current work is more basic: make a natural Minecraft village setup where those questions can later be tested without relying on a staged toy world.
For this check, I ran four provider-backed model lanes through the same small Minecraft LLM-agent harness: two ModelScope lanes using Qwen Plus and Qwen Max, plus OpenAI and Gemini reference lanes.
Outside ModelScope, I stayed within available free-tier or low-quota access. I did not run frontier paid comparisons such as GPT-5.5 or Claude Opus 4.8 for this post, so the results should be read as a harness check, not a frontier-model ranking.
This is not a leaderboard, not a broad model claim, and not a decision about whether interaction history can beat an LLM prior. The point was narrower: check whether the current environment can support concrete Minecraft work, repeated screenshots, inventory review, and blocker analysis across multiple model lanes.
Minecraft natural village - environment check
Each lane started from the same natural village scenario. The actor was asked to create a useful village-adjacent work point: collect wood, craft basic materials, make or use a crafting table, recover from movement blockers, and continue toward simple material work instead of only describing a plan.
This is the practical recipe I used to run provider-backed lanes in the Minecraft LLM-agent harness. The concrete run below used Qwen Plus and Qwen Max through ModelScope API-Inference, but the harness pattern is not tied to that provider.
This cookbook reflects the project state completed on June 30, 2026. It is an operator note, not a leaderboard. The goal is to start from a fresh natural village-adjacent Minecraft world, let a provider-backed actor take bounded actions, and review what happened from screenshots, inventory, world-state scans, and action logs.