# Web Browsing and Navigation (Chinese) on BrowseComp-ZH Source: [Web Browsing and Navigation (Chinese) on BrowseComp-ZH]() Collection index: [llms.txt]() Data updated: 2026-04-23T08:33:20.232Z Evaluation of agent performance on the BrowseComp-ZH dataset for the Web Browsing and Navigation (Chinese) task, measured by avg@3. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Web Browsing and Navigation (Chinese) | | Dataset (including any stated split) | BrowseComp-ZH | | Metric | Avg@3 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Avg@3](): Higher is better; unit: PERCENT. ## Recorded results | Method | Avg@3 | Result date | Report paper | | --- | --- | --- | --- | | OpenAI-GPT-5-high | 65 | Not recorded | 691bfdce6750be83fe5cea20 | | OpenAI-o3 | 58.1 | Not recorded | 691bfdce6750be83fe5cea20 | | MiroThinker-v1.0-72B | 55.6 | Not recorded | 691bfdce6750be83fe5cea20 | | GLM-4.6 | 49.5 | Not recorded | 691bfdce6750be83fe5cea20 | | DeepSeek-V3.1 | 49.2 | Not recorded | 691bfdce6750be83fe5cea20 | | Minimax-M2 | 48.5 | Not recorded | 691bfdce6750be83fe5cea20 | | DeepSeek-V3.2 | 47.9 | Not recorded | 691bfdce6750be83fe5cea20 | | MiroThinker-v1.0-30B | 47.8 | Not recorded | 691bfdce6750be83fe5cea20 | | Tongyi-DeepResearch-30B | 46.7 | Not recorded | 691bfdce6750be83fe5cea20 | | OpenAI DeepResearch | 42.9 | Not recorded | 691bfdce6750be83fe5cea20 | | Claude-4.5-Sonnet | 40.8 | Not recorded | 691bfdce6750be83fe5cea20 | | MiroThinker-v1.0-8B | 40.2 | Not recorded | 691bfdce6750be83fe5cea20 | | DeepMiner-32B-RL | 40.1 | Not recorded | 691bfdce6750be83fe5cea20 | | WebExplorer-8B-RL | 32 | Not recorded | 691bfdce6750be83fe5cea20 | | Claude-4-Sonnet | 29.1 | Not recorded | 691bfdce6750be83fe5cea20 | | Kimi-K2-0905 | 22.2 | Not recorded | 691bfdce6750be83fe5cea20 | ### OpenAI-GPT-5-high Avg@3: 65. Result ID: 69e9d94747f34ce924d10053. [Reporting paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. ### OpenAI-o3 Avg@3: 58.1. Result ID: 69e9d94747f34ce924d10052. [Reporting paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. ### MiroThinker-v1.0-72B Avg@3: 55.6. Result ID: 69e9d94747f34ce924d1005a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"72B"}. This record does not assert independent reproduction. ### GLM-4.6 Avg@3: 49.5. Result ID: 69e9d94747f34ce924d1004b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. ### DeepSeek-V3.1 Avg@3: 49.2. Result ID: 69e9d94747f34ce924d1004d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. ### Minimax-M2 Avg@3: 48.5. Result ID: 69e9d94747f34ce924d1004c. [Reporting paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. ### DeepSeek-V3.2 Avg@3: 47.9. Result ID: 69e9d94747f34ce924d1004e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. ### MiroThinker-v1.0-30B Avg@3: 47.8. Result ID: 69e9d94747f34ce924d10059. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"30B"}. This record does not assert independent reproduction. ### Tongyi-DeepResearch-30B Avg@3: 46.7. Result ID: 69e9d94747f34ce924d10057. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Research Agents"}. This record does not assert independent reproduction. ### OpenAI DeepResearch Avg@3: 42.9. Result ID: 69e9d94747f34ce924d10054. [Reporting paper]() Recorded evaluation configuration: {"Type":"Research Agents"}. This record does not assert independent reproduction. ### Claude-4.5-Sonnet Avg@3: 40.8. Result ID: 69e9d94747f34ce924d10051. [Reporting paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. ### MiroThinker-v1.0-8B Avg@3: 40.2. Result ID: 69e9d94747f34ce924d10058. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Parameters":"8B"}. This record does not assert independent reproduction. ### DeepMiner-32B-RL Avg@3: 40.1. Result ID: 69e9d94747f34ce924d10056. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Research Agents"}. This record does not assert independent reproduction. ### WebExplorer-8B-RL Avg@3: 32. Result ID: 69e9d94747f34ce924d10055. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Research Agents"}. This record does not assert independent reproduction. ### Claude-4-Sonnet Avg@3: 29.1. Result ID: 69e9d94747f34ce924d10050. [Reporting paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. ### Kimi-K2-0905 Avg@3: 22.2. Result ID: 69e9d94747f34ce924d1004f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Type":"Foundation Models with Tools"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.