Odysseys: leaderboard
Odysseys (2026) benchmarks computer-use web agents on realistic long-horizon tasks composed from the browsing journeys of real users across several websites, graded item by item against per-task rubrics. This board is the perfect-rubric rate in percent, the share of tasks with every rubric item satisfied; higher is better.
Metric: Perfect-rubric rate (%: share of tasks with every rubric item satisfied) over all 200 tasks of the Odysseys long-horizon multi-site web tasks run in an OSWorld Ubuntu desktop with Google Chrome, at most 100 steps, maximum reasoning effort, each rubric item judged from the trajectory screenshots and actions by gemini-3.1-flash-lite-preview; higher is better. Source: arxiv.org. Saturation forecast: Around April 2027. 8 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Opus 4.6 | Max | 44.5 | #113 |
| 2 | GPT-5.4 | xHigh | 33.5 | #135 |
| 3 | Claude Sonnet 4.6 | Max | 31 | #173 |
| 4 | Qwen 3.5 9B | 13.5 | #828 | |
| 5 | Qwen 3.5 4B | 10.7 | #1241 | |
| 6 | GPT-5.4 Mini | xHigh | 10.5 | #406 |
| 7 | Qwen 3.5 35B A3B | 6.5 | #492 | |
| 8 | uitars-1.5-7B | 1 | #7905 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=odysseys · How It Works · Data refreshed daily, snapshot 2026-11-21.