List your company

Web Navigation on WebArena

61.7Overall Success RateIBM CUGA
20.82831.43942.0552.661Oct 18, 2025Nov 30, 2025Jan 13, 2026Feb 26, 2026Apr 11, 2026May 25, 2026Jul 8, 2026

Evaluation results

MethodLinks
IBM CUGAModel=-, Access=Proprietary2026.0661.7—————————————————————————————
OpenAI CUAModel=-, Access=Proprietary2026.0658.1—————————————————————————————
WebChallengerModel=GLM-4-32B + Qwen2.5-VL-7B, Access=Open-Source, Evaluation Strategy=zero-shot2026.0656.3—————————————————————————————
Vanilla-IBLLM Backbone=Gemini 1.5 Flash2026.0655.68—————————————————————————99———
ScribeAgentModel=GPT-4o + Qwen2.5-32B, Access=Proprietary2026.0653—————————————————————————————
ASILLM Backbone=Gemini 1.5 Flash2026.0652.75—————————————————————————139.4———
STRUCTUREDAGENTBackbone=Claude 3.5 Sonnet2026.0352.6——————————————4552.872.645.8———————————
Gemini 3 ProCategory=Proprietary, Teacher for A3-SYNTH=true2026.0451.2—————————————————————————————
Vanilla-IBLLM Backbone=Qwen 2.5-72B2026.0650.73—————————————————————————130.3———
WALTModel=GPT-5, Access=Proprietary2026.0650.1—————————————————————————————
ASILLM Backbone=Qwen 2.5-72B2026.0649.08—————————————————————————182.2———
ReasoningBankLLM Backbone=Gemini 1.5 Flash2026.0648.9—————————————————————————124.6———
AgentSymbioticModel=Claude 3.5 + Llama3 8B, Access=Proprietary2026.0648.5—————————————————————————————
Mobile-Agent-v3.5Model=Qwen3-VL-32B, Access=Open-Source, Evaluation Strategy=fine-tuned2026.0648.4—————————————————————————————
Vanilla-IBLLM Backbone=Gemini 1.5 Flash2026.0647.77—————————————————————————45.7———
ReasoningBankLLM Backbone=Qwen 2.5-72B2026.0647.62—————————————————————————156.9———
Vanilla-IBLLM Backbone=Gemini 1.5 Flash2026.0647.48—————————————————————————71.7———
AWMLLM Backbone=Gemini 1.5 Flash2026.0647.48—————————————————————————87.2———
AWMLLM Backbone=Gemini 1.5 Flash2026.0647.43—————————————————————————142.7———
AgentOccamBackbone=Claude 3.5 Sonnet2026.0346.4——————————————46.33860.146.7———————————
AWMLLM Backbone=Qwen 2.5-72B2026.0646.15—————————————————————————178.5———
Vanilla-IBLLM Backbone=Qwen 2.5-72B2026.0645.99—————————————————————————58.8———
AgentOccam-JudgeModel=GPT-4, Access=Proprietary2026.0645.7—————————————————————————————
AgentOccam-JudgeModel=GPT-4-Turbo2025.1045.7——————————————52.343.36738.9————————46.216.7—
ReasoningBankLLM Backbone=Gemini 1.5 Flash2026.0645.45—————————————————————————54.6———
ASILLM Backbone=Gemini 1.5 Flash2026.0644.97—————————————————————————94.6———
ASILLM Backbone=Gemini 1.5 Flash2026.0644.74—————————————————————————82.8———
Vanilla-IBLLM Backbone=Qwen 2.5-72B2026.0644.34—————————————————————————89.7———
ASILLM Backbone=Qwen 2.5-72B2026.0643.67—————————————————————————78.8———
AWMLLM Backbone=Qwen 2.5-72B2026.0643.08—————————————————————————103.6———
ASILLM Backbone=Qwen 2.5-72B2026.0643.08—————————————————————————120.5———
Gemini 3.1 Flash L.Category=Proprietary2026.0442.3—————————————————————————————
Qwen3.5-27BCategory=Open-weight (base)2026.0441.5—————————————————————————————
A3-Qwen3.5-9BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.0441.5—————————————————————————————
Agent-as-AnnotatorsModel=Qwen3.5-9B, Access=Open-Source, Evaluation Strategy=fine-tuned2026.0641.5—————————————————————————————
AWMLLM Backbone=Qwen 2.5-72B2026.0641.35—————————————————————————71.8———
AgentOccamBackbone=GPT 4-o2026.0341.3——————————————44.635.262.332.9———————————
ActiveContextTaskExecutor=Gemini-3.0-flash2026.0441.2——————————————33.326.147.866.7—3941.750.553.843.130.943.3———
ReasoningBankLLM Backbone=Qwen 2.5-72B2026.0641.19—————————————————————————99.1———
AWMLLM Backbone=Gemini 1.5 Flash2026.0641.18—————————————————————————70.8———
ReasoningBankLLM Backbone=Gemini 1.5 Flash2026.0639.93—————————————————————————76.8———
Branch-and-Browse + StePModel=GPT-4o2025.1039.8——————————————47.741.254.737.8————————32.418.8—
ReasoningBankLLM Backbone=Qwen 2.5-72B2026.0639.75—————————————————————————65.4———
API Hybrid AgentModel=GPT-4o2025.1038.9——————————————45.925.751.944.4————————41.216.7—
HMTBackbone=GPT-42026.0338.7————————————34.1—42.233.852.537.65.2——————————
Vanilla-IBLLM Backbone=GPT-4o-mini2026.0638.5—————————————————————————54.3———
WebPilotModel=GPT-4o, Access=Proprietary2026.0637.2—————————————————————————————
WebPilotModel=GPT-4o2025.1037.2——————————————33.936.965.139.4————————24.7——
Full ContextTaskExecutor=Gemini-3.0-flash2026.0436.4——————————————1028.352.266.7—42.233.358.658.335.540.247.4———
GenericAgentModel=Claude 3.5 Sonnet, Access=Proprietary2026.0636.2—————————————————————————————
Vanilla-IBLLM Backbone=GPT-4o-mini2026.0635.89—————————————————————————124.1———
Branch-and-BrowseModel=GPT-4o2025.1035.8——————————————46.834.650.936.7————————26.418.8—
AWMBackbone=GPT-42026.0335.5————————————29.1—43.330.850.931.85.9——————————
Agent Workflow MemoryModel=GPT-4o, Access=Proprietary2026.0635.5—————————————————————————————
AWMModel=GPT-42025.1035.5——————————————42.232.154.735————————29.118.8—
A3-Qwen3.5-4BCategory=A3 fine-tuned, Teacher=Gemini 3 Pro2026.0435.2—————————————————————————————
SynapseTaskExecutor=Gemini-3.0-flash2026.0435.2——————————————26.719.656.543.3—44.641.771.57044.436.653.6———
Vanilla-IBLLM Backbone=GPT-4o-mini2026.0634.59—————————————————————————96.2———
ReasoningBankLLM Backbone=GPT-4o-mini2026.0634.25—————————————————————————123.1———
StePModel=GPT-4-Turbo2025.1033.3——————————————35.833.252.826.7————————32.412.5—
ASILLM Backbone=GPT-4o-mini2026.0633.15—————————————————————————73.4———
StePBackbone=GPT-42026.0333————————————24—303759328.5——————————
ASILLM Backbone=GPT-4o-mini2026.0632.96—————————————————————————138.5———
Training-Free GRPOTaskExecutor=Gemini-3.0-flash2026.0432.7——————————————3017.456.536.7—55.436.170.676.947.850.160.6———
AWMLLM Backbone=GPT-4o-mini2026.0632.24—————————————————————————113.4———
StePBackbone=GPT 4-o2026.0332.1——————————————33.326.956.422.5———————————
Flat RetrievalBackbone=GPT-42026.0332.1————————————25.8—3928.54728.56.5——————————
ActiveContextTaskExecutor=Gemini-2.5-flash2026.0432.1——————————————13.323.947.850—2833.351.653.134.32838.6———
GenericAgentModel=GPT-4o, Access=Proprietary2026.0631.4—————————————————————————————
BasicClaudeActionBackbone=Claude 3.5 Sonnet2026.0331——————————————3730.330.328.1———————————
Qwen3.5-9BCategory=Open-weight (base)2026.0431—————————————————————————————
Full ContextTaskExecutor=Gemini-2.5-flash2026.0430.3——————————————13.321.739.150—31.933.352.766.532.630.442.6———
ActiveContextTaskExecutor=gpt-4o2026.0430.3——————————————13.319.652.256.7—40.622.246.454.733.825.940.8———
AWMLLM Backbone=GPT-4o-mini2026.0629.95—————————————————————————62———
SkillWeaverModel=GPT-4o, Access=Proprietary2026.0629.8—————————————————————————————
AWMLLM Backbone=GPT-4o-mini2026.0629.56—————————————————————————80.4———
SynapseTaskExecutor=Gemini-2.5-flash2026.0429.1——————————————13.31347.840—27.241.75470.233.333.542.9———
SKILL-DISCO + ReActBackbone=GPT-4o2026.0629.06——————————————————5.11——————51.068——0.1215
ASILLM Backbone=GPT-4o-mini2026.0628.93—————————————————————————87.2———
WebarenaReplicationBackbone=Claude 3.5 Sonnet2026.0328.5——————————————31.531.319.728.8———————————
Training-Free GRPOTaskExecutor=Gemini-2.5-flash2026.0427.9——————————————3.321.752.233.3—51.736.162.380.643.764.460.5———
Full ContextTaskExecutor=gpt-4o2026.0427.3——————————————13.31343.553.3—38.92546.454.127.537.541.5———
AutoEvalModel=GPT-42025.1026.9——————————————27.539.620.825————————20.916.7—
ReasoningBankLLM Backbone=GPT-4o-mini2026.0626.38—————————————————————————57.9———
TTIModel=Gemma 3 12B, Access=Open-Source, Evaluation Strategy=fine-tuned2026.0626.1—————————————————————————————
GPT-4.1 baselineBase model=GPT-4.12026.0425.77————————————24.56——30.9115.3826.79———————————
Training-Free GRPOTaskExecutor=gpt-4o2026.0425.5——————————————23.310.943.533.3—50.827.853.864.841.431.349.1———
No MemoryTaskExecutor=gpt-4o2026.0424.8——————————————6.71347.833.3—49.533.363.973.935.635.852.6———
ASIofflineBackbone=GPT-4o2026.0624.63——————————————————5.71——————56.662——0.1269
AutoSurfer_webarenaBase model=Qwen2.52026.0424.23————————————24.56——2026.9226.79———————————
Learn-by-InteractModel=Codestral 22B, Access=Open-Source, Evaluation Strategy=fine-tuned2026.0624.2—————————————————————————————
Qwen3.5-4BCategory=Open-weight (base)2026.0424.1—————————————————————————————
ReActBackbone=GPT-4o2026.0623.89——————————————————5.88——————50.914——0.1152
AutoSurfer_wllmBase model=Qwen2.52026.0423.71————————————22.81——23.6434.6219.64———————————
STRACEPrompt Setting=STRACE (Ours)2026.0723.7————————————16.2——30.836.417.1———————————
Gemini-3.0-flashTaskExecutor=gpt-4o-mini, Memory Management=Zero-Shot Prompting (Curator)2026.0423.6——————————————1017.430.440—37.82554.648.126.13240.7———
BrowserGymModel=GPT-4o2025.1023.5—————————————————————————————
SynapseTaskExecutor=gpt-4o2026.0423——————————————2017.447.823.3—35.216.765.66735.726.946.2———
SKILL-DISCO + CodeActBackbone=GPT-4o2026.0622.91——————————————————8.47——————85.649——0.1606
AgentTrekModel=Qwen2.5-32B, Access=Open-Source, Evaluation Strategy=fine-tuned2026.0622.4—————————————————————————————