List your company

Web Agent on WebArena Lite

21.2SRWEASEL (10K steps)
4.8729.11113.3517.589May 19, 2026

Evaluation results

MethodLinks
WEASEL (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=8.3 hr, Speed-up=10.7×2026.0521.2
Pruning + LLM-Judge (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=7.0 hr, Speed-up=12.6×2026.0519.4
Full (52K steps)Model=Qwen3-8B, # Data=52K, # Epochs=2, Time=88.5 hr, Speed-up=1.0×2026.0517.7
Pruning (52K steps)Model=Qwen3-8B, # Data=52K, # Epochs=2, Time=44.0 hr, Speed-up=2.0×2026.0517.6
Pruning + Sampling (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=7.0 hr, Speed-up=12.6×2026.0516.5
Qwen3-8BModel=Qwen3-8B2026.0516.4
WEASEL (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.0514.5
WEASEL (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.0511.5
Full (52K steps)Model=Qwen2.5-7B-Instruct, # Data=52K, # Epochs=4, Time=136.0 hr, Speed-up=1.0×2026.0510.9
Pruning (52K steps)Model=Qwen2.5-7B-Instruct, # Data=52K, # Epochs=4, Time=62.0 hr, Speed-up=2.2×2026.059.7
Pruning + Sampling (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.059.1
Full (52K steps)Model=Gemma3-4B-IT, # Data=52K, # Epochs=2, Time=80.0 hr, Speed-up=1.0×2026.059.1
Pruning (52K steps)Model=Gemma3-4B-IT, # Data=52K, # Epochs=2, Time=30.0 hr, Speed-up=2.7×2026.059.1
Pruning + LLM-Judge (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.058.5
Pruning + Sampling (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.058.5
Gemma3-4B-ITModel=Gemma3-4B-IT2026.056.7
Pruning + LLM-Judge (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.056.7
Qwen2.5-7B-InstructModel=Qwen2.5-7B-Instruct2026.055.5