Leaderboard

System / Submission Score Organization Reported Source
GPT-5.6 Sol New
62.6% OpenAI Source
Claude Opus 4.8 (batched tools) New
54.8% Anthropic Source
GPT-5.5 (batched tools) New
49.5% OpenAI Source
Claude Opus 4.8 New
49.33% Anthropic Source
Claude Opus 4.7 New
49.1% Anthropic Source
Claude Opus 4.7 (batched tools) New
48.91% Anthropic Source
Claude Sonnet 4.6 (max thinking) New
41.5% Anthropic Source
Claude Sonnet 4.6 (medium thinking) New
33.9% Anthropic Source
MiniMax M3 New
22.3% MiniMax Source
Kimi 2.6 New
22.1% Moonshot AI Source
Qwen 3.7-Plus New
21.5% Alibaba Source

About this benchmark

OSWorld 2.0 evaluates computer-use agents on 108 long-horizon, end-to-end desktop workflows spanning everyday and professional tasks across self-hosted websites, office suites, files, and multi-application pipelines.

It is far harder than OSWorld 1.0: tasks take human users a median of about 1.6 hours, require an average of roughly 318 tool calls (vs about 30 in OSWorld 1.0), and 69.6% run longer than an hour, stressing cross-source reasoning, implicit-state inference, streaming interaction, and visual-spatial precision.

Scores here are not comparable to the OSWorld (1.0/Verified) leaderboard: the task set, step budgets, and metrics all differ, so use this page only for within-benchmark ranking.

Rows are self-reported (benchmark team or OpenAI); independent third-party results are not yet available, and GPT-5.6 Sol's binary completion is unpublished.

Binary completion is deliberately low (best about 20.6%, Claude Opus 4.8); we rank on partial score instead, so a row's partial score is not comparable to OSWorld 1.0/Verified pass rates.

Example tasks

Three public tasks quoted from benchmark sources:

Methodology

  • Tasks run in real VM desktop environments with execution-based validators that check final state against many fine-grained checkpoints (averaging 27.25 per task).
  • OSWorld 2.0 scores two ways: binary completion (all checkpoints passed) and a partial score (fraction of checkpoints reached). We rank on the partial score — it differentiates systems far better than the low binary rates and matches how the GPT-5.6 result is reported — with each row's binary completion noted. Tracked scores use the default 500-step budget.
  • Most rows are author-run by the benchmark team on the official OSWorld 2.0 harness; the GPT-5.6 Sol row is OpenAI self-reported at launch. Reasoning effort, tool-call mode, and step budget are reported per row and materially affect scores.
  • We track public results with source URLs and note that no independent third-party reproduction exists yet.

Related benchmarks

Compare this benchmark with related pages from the hub:

Back to benchmark hub

Frequently asked questions

Which system is currently best on OSWorld 2.0? +
GPT-5.6 Sol is the system/agent setup currently leading with a tracked score of 62.6%. This ranking reflects submitted system setups (model plus tools and policy), not just a base model. Based on our latest tracked results, last updated Jul 10, 2026.
What should I read into a OSWorld 2.0 score? +
OSWorld 2.0 scores are most useful for within-benchmark ranking. Read the Notes column to understand setup context, and use the methodology section before making procurement or architecture decisions.
Are these independently verified? +
Not always. Some rows are independently benchmarked and some are team-reported. Use each source link and notes field to verify evidence level before drawing strong conclusions.