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

#ModelSettingScoreOverall rank
1Claude Opus 4.6Max44.5#113
2GPT-5.4xHigh33.5#135
3Claude Sonnet 4.6Max31#173
4Qwen 3.5 9B13.5#828
5Qwen 3.5 4B10.7#1241
6GPT-5.4 MinixHigh10.5#406
7Qwen 3.5 35B A3B6.5#492
8uitars-1.5-7B1#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.