List your company

Web Agent on WorkArena L2

4.7Success RateWEASEL (10K steps)
-0.1881.0812.353.619May 19, 2026

Evaluation results

MethodLinks
WEASEL (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.054.7
WEASEL (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=8.3 hr, Speed-up=10.7×2026.054.3
Pruning + LLM-Judge (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=7.0 hr, Speed-up=12.6×2026.053.8
Pruning + Sampling (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=7.0 hr, Speed-up=12.6×2026.053.4
Pruning + Sampling (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.053
Pruning + LLM-Judge (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.053
WEASEL (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.053
Pruning (52K steps)Model=Qwen3-8B, # Data=52K, # Epochs=2, Time=44.0 hr, Speed-up=2.0×2026.052.6
Pruning + Sampling (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.052.1
Pruning + LLM-Judge (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.052.1
Full (52K steps)Model=Qwen3-8B, # Data=52K, # Epochs=2, Time=88.5 hr, Speed-up=1.0×2026.052.1
Qwen3-8BModel=Qwen3-8B2026.051.7
Full (52K steps)Model=Qwen2.5-7B-Instruct, # Data=52K, # Epochs=4, Time=136.0 hr, Speed-up=1.0×2026.050.4
Pruning (52K steps)Model=Qwen2.5-7B-Instruct, # Data=52K, # Epochs=4, Time=62.0 hr, Speed-up=2.2×2026.050.4
Qwen2.5-7B-InstructModel=Qwen2.5-7B-Instruct2026.050
Gemma3-4B-ITModel=Gemma3-4B-IT2026.050
Full (52K steps)Model=Gemma3-4B-IT, # Data=52K, # Epochs=2, Time=80.0 hr, Speed-up=1.0×2026.050
Pruning (52K steps)Model=Gemma3-4B-IT, # Data=52K, # Epochs=2, Time=30.0 hr, Speed-up=2.7×2026.050