RankingOSWorld · 2.0 August2026 task release

OSWorld · 2.0 August2026 task release

Data updated 12 Sept 2026

Bucket
Agentic
Unit
percent
Direction
Higher is better
Version
2.0 August2026 task release
Display harness
Claude Fable 5.1 and Claude Mythos 5.1 System Card
Board
https://www.anthropic.com/claude-fable-5-1-mythos-5-1-system-card

Compare published benchmark results with category weights →

Models

ModelScoreHarnessEvidenceSource-recorded date
Claude Fable 5.1Anthropic77.9%
Reported settings & source

partial pass@1;108tasks; five runs;1080p;500steps; max effort; Opus4.8grader; task fixes; Fable safety interventions score zero.

Same-condition reruns; supersedes earlier OSWorld2results and incompatible with previous task files. Fable is the safeguarded deployed configuration; selected tasks may use disclosed Opus fallback, except evaluations explicitly counting safety blocks as failures.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.3 · reviewed 2026-09-12

Claude Fable 5.1 and Claude Mythos 5.1 System Cardlab self-report2026-09-12
Claude Opus 5Anthropic75.4%
Reported settings & source

partial pass@1;108tasks; five runs;1080p;500steps; max effort; Opus4.8grader; task fixes; Fable safety interventions score zero.

Same-condition reruns; supersedes earlier OSWorld2results and incompatible with previous task files.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.3 · reviewed 2026-09-12

Claude Fable 5.1 and Claude Mythos 5.1 System Cardlab self-report2026-09-12
Claude Fable 5Anthropic72.9%
Reported settings & source

partial pass@1;108tasks; five runs;1080p;500steps; max effort; Opus4.8grader; task fixes; Fable safety interventions score zero.

Same-condition reruns; supersedes earlier OSWorld2results and incompatible with previous task files. Fable is the safeguarded deployed configuration; selected tasks may use disclosed Opus fallback, except evaluations explicitly counting safety blocks as failures.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.3 · reviewed 2026-09-12

Claude Fable 5.1 and Claude Mythos 5.1 System Cardlab self-report2026-09-12
Claude Fable 5Anthropic36.1%
Reported settings & source

strict pass@1;108tasks; five runs;1080p;500steps; max effort; Opus4.8grader; task fixes; Fable safety interventions score zero.

Same-condition reruns; supersedes earlier OSWorld2results and incompatible with previous task files. Fable is the safeguarded deployed configuration; selected tasks may use disclosed Opus fallback, except evaluations explicitly counting safety blocks as failures.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.3 · reviewed 2026-09-12

Claude Fable 5.1 and Claude Mythos 5.1 System Cardlab self-report2026-09-12
Claude Fable 5.1Anthropic41.7%
Reported settings & source

strict pass@1;108tasks; five runs;1080p;500steps; max effort; Opus4.8grader; task fixes; Fable safety interventions score zero.

Same-condition reruns; supersedes earlier OSWorld2results and incompatible with previous task files. Fable is the safeguarded deployed configuration; selected tasks may use disclosed Opus fallback, except evaluations explicitly counting safety blocks as failures.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.3 · reviewed 2026-09-12

Claude Fable 5.1 and Claude Mythos 5.1 System Cardlab self-report2026-09-12
Claude Opus 5Anthropic39.6%
Reported settings & source

strict pass@1;108tasks; five runs;1080p;500steps; max effort; Opus4.8grader; task fixes; Fable safety interventions score zero.

Same-condition reruns; supersedes earlier OSWorld2results and incompatible with previous task files.

Claude Fable 5.1 and Claude Mythos 5.1 System Card · 8.14.3 · reviewed 2026-09-12

Claude Fable 5.1 and Claude Mythos 5.1 System Cardlab self-report2026-09-12