List your company

Web-based Interaction on MiniWoB

74.7Success RateGemini 3 Pro
9.28426.26743.2560.233Apr 9, 2026Apr 15, 2026Apr 22, 2026Apr 29, 2026May 5, 2026May 12, 2026May 19, 2026

Evaluation results

MethodLinks
Gemini 3 ProCategory=Proprietary, Teacher for A3-SYNTH=true2026.0474.7
Gemini 3.1 Flash L.Category=Proprietary2026.0474.1
GPT-5Harness=GenericAgent, Params=-2026.0471.5
Qwen3.5-27BCategory=Open-weight (base)2026.0470.9
Claude 4 SonnetHarness=GenericAgent, Params=-2026.0470.7
A3-Qwen3.5-9BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.0469
A3-Qwen3.5-9BHarness=GenericAgent, Params=9B2026.0469
A3-Qwen3.5-4BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.0466.9
GPT-oss-120BHarness=GenericAgent, Params=120B2026.0466.4
Qwen3.5-9BCategory=Open-weight (base)2026.0463.2
Qwen3.5-9B (base)Harness=GenericAgent, Params=9B2026.0463.2
Pruning + LLM-Judge (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=7.0 hr, Speed-up=12.6×2026.0561.9
WEASEL (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=8.3 hr, Speed-up=10.7×2026.0561.9
Pruning + Sampling (10K steps)Model=Qwen3-8B, # Data=10K, # Epochs=2, Time=7.0 hr, Speed-up=12.6×2026.0561.4
Qwen3.5-4BCategory=Open-weight (base)2026.0461.1
Qwen3-8BModel=Qwen3-8B2026.0561.1
Full (52K steps)Model=Qwen3-8B, # Data=52K, # Epochs=2, Time=88.5 hr, Speed-up=1.0×2026.0559.4
WEASEL (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.0548
Pruning (52K steps)Model=Qwen2.5-7B-Instruct, # Data=52K, # Epochs=4, Time=62.0 hr, Speed-up=2.2×2026.0547.7
Pruning + Sampling (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.0546.7
Pruning + LLM-Judge (10K steps)Model=Qwen2.5-7B-Instruct, # Data=10K, # Epochs=4, Time=12.0 hr, Speed-up=11.3×2026.0545.4
Full (52K steps)Model=Qwen2.5-7B-Instruct, # Data=52K, # Epochs=4, Time=136.0 hr, Speed-up=1.0×2026.0544.6
Qwen2.5-7B-InstructModel=Qwen2.5-7B-Instruct2026.0541.8
Pruning (52K steps)Model=Qwen3-8B, # Data=52K, # Epochs=2, Time=44.0 hr, Speed-up=2.0×2026.0540.3
A3-Qwen3.5-2BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.0438.6
WEASEL (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.0530.6
Pruning + Sampling (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.0529.4
Pruning + LLM-Judge (10K steps)Model=Gemma3-4B-IT, # Data=10K, # Epochs=2, Time=6.4 hr, Speed-up=12.5×2026.0529.3
Full (52K steps)Model=Gemma3-4B-IT, # Data=52K, # Epochs=2, Time=80.0 hr, Speed-up=1.0×2026.0528.6
Pruning (52K steps)Model=Gemma3-4B-IT, # Data=52K, # Epochs=2, Time=30.0 hr, Speed-up=2.7×2026.0528.2
Gemma3-4B-ITModel=Gemma3-4B-IT2026.0527.4
Qwen3.5-2BCategory=Open-weight (base)2026.0411.8