Reported in recent model launches
These model reports include this benchmark. Their harnesses, task subsets, scoring policies, and resource budgets can differ; follow each report’s evaluation notes before joining the numbers.
What it measures
Interactive environments assess how an agent explores, learns rules, and adapts to unfamiliar tasks.
How to read the result
Measure the relationship between successful adaptation and the interactions spent discovering how the environment works.
Limits and comparison traps
Harness behavior and interaction budgets are part of the score. A reported percentage is not interchangeable with static ARC-AGI grid accuracy.
Benchmark reference notes
Interactive, action-based environment benchmark where agents explore unknown grid-world game rules and solve goals within an action budget.
Where this fits in an evaluation suite
Ask what the task actually requires: recall, deduction, search, or a mixture. Separate closed-book reasoning from retrieval and tool-assisted problem solving.
Start with a capability hypothesis, then choose a second test with a different failure mode. Keep the checkpoint, reasoning effort, agent tools, sampling policy, and scoring procedure fixed when measuring a training intervention. Record failures and missing outputs in the denominator.
A reproducible comparison
Pin the benchmark release, task split, model configuration, tools, sampling budget, and evaluation harness described by the primary source.
Publish the exact run configuration, item coverage, score units, and available uncertainty. If a source supplies only an aggregate or a single run, preserve that limit. A new model name or a rounded score alone does not establish a capability improvement.
PRIMARY EVIDENCE & FURTHER READING
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.