Codesota · Models · Agent S w/ Claude-3.51 results · 1 benchmarks
Model card

Agent S w/ Claude-3.5.

unknown
§ 02 · Benchmarks

Every benchmark Agent S w/ Claude-3.5 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01OSWorldAgentic AI · Web & Desktop Agentssuccess-rate20.5%#23/28source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Agent S w/ Claude-3.5 actually performs.

Agentic AI
1
benchmark
avg rank #23.0
§ 04 · Papers

1 paper with results for Agent S w/ Claude-3.5.

  1. 2024-10-10· 1 result

    Agent S: An Open Agentic Framework that Uses Computers Like a Human

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
1
result
0 of 1 rows marked verified.