Web Browsing on BrowseComp-Plus
83.92AccuracyCoT-SC
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| CoT-SCLLM Backbone=GPT-52026.06 | 83.92 | — | — | — | — | — | — | — | — | 66.8 | |
| CoTLLM Backbone=GPT-52026.06 | 83.33 | — | — | — | — | — | — | — | — | 12.7 | |
| CoT-SCLLM Backbone=Gemini-2.5-Pro2026.06 | 83.04 | — | — | — | — | — | — | — | — | 72.97 | |
| MaASLLM Backbone=Gemini-2.5-Pro2026.06 | 81.85 | — | — | — | — | — | — | — | — | 210.86 | |
| MaASLLM Backbone=GPT-52026.06 | 81.55 | — | — | — | — | — | — | — | — | 125.6 | |
| CoTLLM Backbone=Gemini-2.5-Pro2026.06 | 79.17 | — | — | — | — | — | — | — | — | 14.95 | |
| MAS-OrchestraLLM Backbone=GPT-52026.06 | 77.91 | — | — | — | — | — | — | — | — | 87.1 | |
| DyLANLLM Backbone=GPT-52026.06 | 76.19 | — | — | — | — | — | — | — | — | 46 | |
| AFlowLLM Backbone=GPT-52026.06 | 75.79 | — | — | — | — | — | — | — | — | 190 | |
| MAS-ZeroLLM Backbone=Gemini-2.5-Pro2026.06 | 73.81 | — | — | — | — | — | — | — | — | 992 | |
| AFlowLLM Backbone=Gemini-2.5-Pro2026.06 | 73.61 | — | — | — | — | — | — | — | — | 849.74 | |
| MAS-ZeroLLM Backbone=GPT-52026.06 | 71.63 | — | — | — | — | — | — | — | — | 1,370.4 | |
| CoT-SCLLM Backbone=GPT-OSS-120B2026.06 | 70.43 | — | — | — | — | — | — | — | — | 5.6 | |
| MaASLLM Backbone=GPT-OSS-120B2026.06 | 68.85 | — | — | — | — | — | — | — | — | 6.3 | |
| CoTLLM Backbone=GPT-OSS-120B2026.06 | 68.65 | — | — | — | — | — | — | — | — | 0.9 | |
| ADASLLM Backbone=GPT-52026.06 | 67.63 | — | — | — | — | — | — | — | — | 650.2 | |
| CoT-SCLLM Backbone=GPT-4o2026.06 | 67.26 | — | — | — | — | — | — | — | — | 130.2 | |
| AFlowLLM Backbone=GPT-OSS-120B2026.06 | 66.66 | — | — | — | — | — | — | — | — | 9.8 | |
| MAS-OrchestraLLM Backbone=GPT-OSS-120B2026.06 | 66.46 | — | — | — | — | — | — | — | — | 8.3 | |
| DyLANLLM Backbone=Gemini-2.5-Pro2026.06 | 66.07 | — | — | — | — | — | — | — | — | 286.92 | |
| MaASLLM Backbone=GPT-4o2026.06 | 64.88 | — | — | — | — | — | — | — | — | 126.7 | |
| ADASLLM Backbone=Gemini-2.5-Pro2026.06 | 64.88 | — | — | — | — | — | — | — | — | 364 | |
| MAS-OrchestraLLM Backbone=GPT-4o2026.06 | 64.85 | — | — | — | — | — | — | — | — | 127.9 | |
| DyLANLLM Backbone=GPT-OSS-120B2026.06 | 64.68 | — | — | — | — | — | — | — | — | 4.5 | |
| CoTLLM Backbone=GPT-4o2026.06 | 64.48 | — | — | — | — | — | — | — | — | 33.1 | |
| DyLANLLM Backbone=GPT-4o2026.06 | 63.29 | — | — | — | — | — | — | — | — | 77.8 | |
| MAS-ZeroLLM Backbone=GPT-OSS-120B2026.06 | 61.9 | — | — | — | — | — | — | — | — | 63.6 | |
| MAS-ZeroLLM Backbone=GPT-4o2026.06 | 61.89 | — | — | — | — | — | — | — | — | 2,675.5 | |
| AFlowLLM Backbone=GPT-4o2026.06 | 59.92 | — | — | — | — | — | — | — | — | 95.5 | |
| ADASLLM Backbone=GPT-4o2026.06 | 57.2 | — | — | — | — | — | — | — | — | 409.4 | |
| ADASLLM Backbone=GPT-OSS-120B2026.06 | 56.15 | — | — | — | — | — | — | — | — | 9.2 | |
| AggAgentK=2, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | — | — | 58.44 | — | |
| AggAgentK=4, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | — | — | 66.22 | — | |
| AggAgentK=8, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | — | — | 71.33 | — | |
| BoNK=2, Model=GLM-4.7-Flash2026.04 | — | — | — | — | 57.05 | — | — | — | — | — | |
| BoNK=4, Model=GLM-4.7-Flash2026.04 | — | — | — | — | 62.81 | — | — | — | — | — | |
| BoNK=8, Model=GLM-4.7-Flash2026.04 | — | — | — | — | 68.67 | — | — | — | — | — | |
| FewToolK=2, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | 54.31 | — | — | — | — | |
| FewToolK=4, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | 58.86 | — | — | — | — | |
| FewToolK=8, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | 62 | — | — | — | — | |
| MVK=2, Model=GLM-4.7-Flash2026.04 | — | — | 48.71 | — | — | — | — | — | — | — | |
| MVK=4, Model=GLM-4.7-Flash2026.04 | — | — | 54.1 | — | — | — | — | — | — | — | |
| MVK=8, Model=GLM-4.7-Flash2026.04 | — | — | 59.33 | — | — | — | — | — | — | — | |
| PassK=1, Model=GLM-4.7-Flash2026.04 | — | 49.08 | — | — | — | — | — | — | — | — | |
| PassK=2, Model=GLM-4.7-Flash2026.04 | — | 59.64 | — | — | — | — | — | — | — | — | |
| PassK=4, Model=GLM-4.7-Flash2026.04 | — | 67.36 | — | — | — | — | — | — | — | — | |
| PassK=8, Model=GLM-4.7-Flash2026.04 | — | 72 | — | — | — | — | — | — | — | — | |
| SolAggK=2, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | 54.67 | — | — | — | |
| SolAggK=4, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | 63.33 | — | — | — | |
| SolAggK=8, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | 70.67 | — | — | — | |
| SummAggK=2, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | — | 58 | — | — | |
| SummAggK=4, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | — | 63.33 | — | — | |
| SummAggK=8, Model=GLM-4.7-Flash2026.04 | — | — | — | — | — | — | — | 70.67 | — | — | |
| WMVK=2, Model=GLM-4.7-Flash2026.04 | — | — | — | 57.02 | — | — | — | — | — | — | |
| WMVK=4, Model=GLM-4.7-Flash2026.04 | — | — | — | 63.02 | — | — | — | — | — | — | |
| WMVK=8, Model=GLM-4.7-Flash2026.04 | — | — | — | 68.67 | — | — | — | — | — | — |