Model results
Vals Minecraft Research Run
Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.
Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.
Vals Minecraft — tech-tree rung
- Source
- Vals AI (reviewed publisher results)
- Version
- 2026-09-single-run-141h-keepinventory
- Measurement date
- Not reported
- Metric
- /15 stages · Higher is better
- Evaluation scope
- One 141-hour run; Normal Survival; keepInventory ON; reached Ender pearl (rung 13/15); Eye of Ender and The End not reached; 6 blaze rods, 3 Ender pearls, 0 Eyes of Ender; 175 item types evidenced; 548 deaths; pixels and keyboard/mouse computer use; harness and reasoning effort unspecified. Single-run observation, not a success rate or cross-model speed ranking. Published 2026-09-15; result date not supplied; captured 2026-09-17.
Fewer than two comparable models. No ranking is assigned. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.
GPT-6 Astra
openai/gpt-6-astra-20260903
13/15 stages
View modelEvidence independent