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
Long-horizon computer workflows extend evaluation across applications, files, and realistic task sequences.
How to read the result
Inspect both checkpoint credit and complete-task success. A useful intermediate artifact does not mean the entire workflow was completed.
Limits and comparison traps
Offline subsets, environment patches, action interfaces, screen resolution, and compaction policies can change the result substantially.
Benchmark reference notes
Expanded multi-app desktop computer-use benchmark with partial and binary state graders.
Epoch data and evaluation setting
Epoch AI publishes this benchmark in its capability collection. Imported rows retain the published score column and model configuration. Original authors and evaluation providers remain credited in the result references.
Epoch attribution and score coverage
Data is attributed to Epoch AI under CC BY 4.0, with original evaluation providers credited in the linked source snapshots. Scores are imported only where a published mapping identifies the field and its scale; missing or incompatible records are omitted rather than assigned zero.
Where this fits in an evaluation suite
A transcript that says “done” is weaker evidence than the verified final state. Track policy violations, recoveries, and invalid attempts alongside success.
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
- OSWorld 2.0: Benchmarking computer-use agents on long-horizon real-world tasks ↗
- Epoch AI · benchmark and methodology ↗
- Capabilities & benchmarking — retained external evaluation records ↗
Reviewed 2026-10-26. Explanation and interpretation by RLTasks. Benchmark ownership remains with its original authors.