OSWorld 2.1 (offline set, partial)
Partial score on the OSWorld 2.1 offline set (82 tasks).
- Category
- Computer use
- Unit
- Percent (%)
- Higher is better
- Comparison groups
- 1total
- Currently available model rankings · Ranked results: 3
- All models (records): Groups: 2 · Entries: 7
Rankings
Values with different source types (official, third-party, paper) or measurement conditions cannot be compared, so rankings are separated by comparison group (the same source, or sources verified to use the same conditions).
Rankings include only models currently available in Claude Code / Codex, excluding legacy models.
official results (Introducing Claude Fable 5.2 and Claude Mythos 5.2)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | not stated | 89.3% | — | Anthropic | Introducing Claude Fable 5.2 and Claude Mythos 5.2Retrieved 2026-11-12 · Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.Source excerpt89.3%Location Table, OSWorld 2.1 (offline set, partial) row: 89.3 |
| 2 | Claude Opus 5.5 | not stated | 87.2% | — | Anthropic | Introducing Claude Fable 5.2 and Claude Mythos 5.2Retrieved 2026-11-12 · Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.Source excerpt87.2%Location Table, OSWorld 2.1 (offline set, partial) row: 87.2 |
| 3 | GPT-6 Astra | not stated | 79.5% | — | not stated | Introducing Claude Fable 5.2 and Claude Mythos 5.2Retrieved 2026-11-12 · Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted. Values for other vendor models (as listed by Anthropic).Source excerpt79.5%Location Table, OSWorld 2.1 (offline set, partial) row: 79.5 |
All model rankings (records)
These rankings are recalculated by comparison group including legacy models and models unavailable in Claude Code / Codex. They differ from the rankings above because the set of models differs.
Show rankings including legacy and unavailable models (entries: 7)
official results (Introducing Claude Fable 5.2 and Claude Mythos 5.2)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | not stated | 89.3% | — | Anthropic | Introducing Claude Fable 5.2 and Claude Mythos 5.2Retrieved 2026-11-12 · Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.Source excerpt89.3%Location Table, OSWorld 2.1 (offline set, partial) row: 89.3 |
| 2 | Claude Opus 5.5 | not stated | 87.2% | — | Anthropic | Introducing Claude Fable 5.2 and Claude Mythos 5.2Retrieved 2026-11-12 · Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.Source excerpt87.2%Location Table, OSWorld 2.1 (offline set, partial) row: 87.2 |
| 3 | Claude Fable 5.1 | not stated | 83.5% | — | Anthropic | Introducing Claude Fable 5.2 and Claude Mythos 5.2Retrieved 2026-11-12 · Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted.Source excerpt83.5%Location Table, OSWorld 2.1 (offline set, partial) row: 83.5 |
| 4 | Gemini 4 Carbon | not stated | 81.5% | — | not stated | Introducing Claude Fable 5.2 and Claude Mythos 5.2Retrieved 2026-11-12 · Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted. Values for other vendor models (as listed by Anthropic).Source excerpt81.5%Location Table, OSWorld 2.1 (offline set, partial) row: 81.5 |
| 5 | GPT-6 Astra | not stated | 79.5% | — | not stated | Introducing Claude Fable 5.2 and Claude Mythos 5.2Retrieved 2026-11-12 · Vendor-reported value. table note: Scores for Fable 5.2, Fable 5.1, and Opus 5.5 show results with safeguards on unless otherwise noted. All scores show each model’s highest-available effort unless otherwise noted. Values for other vendor models (as listed by Anthropic).Source excerpt79.5%Location Table, OSWorld 2.1 (offline set, partial) row: 79.5 |
official results (Gemini 4 Carbon (Google DeepMind models page, benchmark table))
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | High | 81.5% | — | Gemini 4 Carbon (Google DeepMind models page, benchmark table)Retrieved 2026-11-12 · Vendor-reported value. Google published table. methodology PDF: Gemini 4 Carbon/Argon used the highest Gemini API thinking setting, pass@1, and a single trial. Row-specific source: self-measured. 82-task offline subset, maximum of 3 runs, partial scoreSource excerptOSWorld-2.1 (offline subset): Gemini 4 Carbon 81.5 | |
| 2 | Gemini 4 Argon | High | 74.7% | — | Gemini 4 Carbon (Google DeepMind models page, benchmark table)Retrieved 2026-11-12 · Vendor-reported value. Google published table. methodology PDF: Gemini 4 Carbon/Argon used the highest Gemini API thinking setting, pass@1, and a single trial. Row-specific source: self-measured. 82-task offline subset, maximum of 3 runs, partial scoreSource excerptOSWorld-2.1 (offline subset): Gemini 4 Argon 74.7 |