Live
Odysseys2: a long-horizon web agent benchmark
Trending storyPast story
Odysseys2: a long-horizon web agent benchmark
1 reports1 outlets23 days agoUpdate
The story so far
AI overview
GPT-6 Astra performed the best in the Odyssey2 long-term web agent benchmark, completing 47 tasks with an average score of 84.6. The benchmark includes 100 real web tasks, each with 8-12 pass/fail checks, involving 15 agents. Opus 5.5 efficient mode completed 18 tasks with an average score of 71.2.
AI-written from the reports · Updated 22 days ago
Latest27 Oct, 08:00
Odysseys2: A Long-Term Web Intelligent Agent BenchmarkCoverage timeline
Follow the coverage to see every side of the story.
27 Oct
- Browser UseOdysseys2: a long-horizon web agent benchmark
GPT-6 Astra performs best in the Odysseys2 long-term web intelligence agent benchmark, completing 47 tasks with an average score of 84.6. The benchmark includes 100 real web tasks, each with 8-12 pass/fail checks, 15 agents participated in the test, among which Opus 5.5 efficient mode completed 18 tasks with an average score of 71.2.