A3-Qwen3.5-9B: benchmark results

Provider: Other.

Aggregate Rating 1660 ± 42, rank #555 of 10916 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
BrowserGym VisualWebArena33.7Success rate (%, GenericAgent unless named)100
BrowserGym WebArena42.1Success rate (%, GenericAgent unless named)90.9
VisualWebArena33.7Success Rate (%)88.7
BrowserGym MiniWoB69Success Rate (%)66.7
WebArena42.1Success Rate (%)63.8
BrowserGym WorkArena L151.5Success Rate (%)60
BrowserGym WorkArena L210.6Success Rate (%)53.8
MedCUA-Bench - Intent Goals1.4Strict success rate (%) on the 216 intent-goal tasks (the cl15.6
MedCUA-Bench1.2Strict success rate (%) over all 432 screenshot-only clinica12.5
MedCUA-Bench - Step Goals0.9Strict success rate (%) on the 216 step-goal tasks (the same9.4

Interactive version: theaggregate.ai/model?slug=a3-qwen3-5-9b · How It Works · Data refreshed daily, snapshot 2026-11-08.