Odysseys - Rubric Score: 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 mean share of rubric items satisfied per task, in percent; higher is better.

Metric: Mean rubric score (%: share of a task's rubric items satisfied, averaged over the 200 tasks) on 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 4.6Max68.9#114
2GPT-5.4xHigh55.4#138
3Claude Sonnet 4.6Max49.8#179
4Qwen 3.5 4B42.9#1270
5Qwen 3.5 9B42.6#838
6GPT-5.4 MinixHigh38.4#409
7Qwen 3.5 35B A3B28.5#494
8uitars-1.5-7B10#7957

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=odysseys-rubric-score · How It Works · Data refreshed daily, snapshot 2026-11-22.