# Long-horizon agentic tasks on BrowseComp-ZH Our Settings Source: [Long-horizon agentic tasks on BrowseComp-ZH Our Settings]() Collection index: [llms.txt]() Data updated: 2026-03-31T09:42:17.305Z Evaluation of model performance on long-horizon agentic tasks using the BrowseComp-ZH Our Settings configuration, measured by Pass@1. 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 | Long-horizon agentic tasks | | Dataset (including any stated split) | BrowseComp-ZH Our Settings | | Metric | Pass@1 | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 25 of 25 | | 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 - [Pass@1](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 | Result date | Report paper | | --- | --- | --- | --- | | AgentSwing | 71.3 | Not recorded | 69cb555c0636e5bf4afca207 | | DeepSeek-v3.2 | 70.2 | Not recorded | 69cb555c0636e5bf4afca207 | | DeepSeek-v3.2 | 69.9 | Not recorded | 69cb555c0636e5bf4afca207 | | DeepSeek-v3.2 | 69.2 | Not recorded | 69cb555c0636e5bf4afca207 | | Gemini-3.0-Pro | 66.8 | Not recorded | 69cb555c0636e5bf4afca207 | | MiroThinker-v1.5-30B-A3B | 66.8 | Not recorded | 69cb555c0636e5bf4afca207 | | Claude-4.5-Opus | 62.4 | Not recorded | 69cb555c0636e5bf4afca207 | | DeepSeek-v3.2 | 61.6 | Not recorded | 69cb555c0636e5bf4afca207 | | OpenAI-o3 | 58.1 | Not recorded | 69cb555c0636e5bf4afca207 | | AgentSwing | 56.7 | Not recorded | 69cb555c0636e5bf4afca207 | | Tongyi-DR-30B-A3B | 53.9 | Not recorded | 69cb555c0636e5bf4afca207 | | Tongyi-DR-30B-A3B | 50.1 | Not recorded | 69cb555c0636e5bf4afca207 | | Tongyi-DR-30B-A3B | 49.1 | Not recorded | 69cb555c0636e5bf4afca207 | | AgentFold-30B-A3B | 47.3 | Not recorded | 69cb555c0636e5bf4afca207 | | Tongyi-DR-30B-A3B | 47.1 | Not recorded | 69cb555c0636e5bf4afca207 | | IterResearch-30B-A3B | 45.2 | Not recorded | 69cb555c0636e5bf4afca207 | | AgentFounder-30B-A3B | 43.3 | Not recorded | 69cb555c0636e5bf4afca207 | | OpenAI DeepResearch | 42.9 | Not recorded | 69cb555c0636e5bf4afca207 | | DeepMiner-32B-RL | 40.1 | Not recorded | 69cb555c0636e5bf4afca207 | | AgentSwing | 38 | Not recorded | 69cb555c0636e5bf4afca207 | | GPT-OSS-120B | 33.6 | Not recorded | 69cb555c0636e5bf4afca207 | | GPT-OSS-120B | 31.5 | Not recorded | 69cb555c0636e5bf4afca207 | | GPT-OSS-120B | 30.8 | Not recorded | 69cb555c0636e5bf4afca207 | | GPT-OSS-120B | 28.4 | Not recorded | 69cb555c0636e5bf4afca207 | | ASearcher-Web-32B | 15.6 | Not recorded | 69cb555c0636e5bf4afca207 | ### AgentSwing Pass@1: 71.3. Result ID: 69cb96f447f34ce924b44326. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"DeepSeek-v3.2"}. This record does not assert independent reproduction. ### DeepSeek-v3.2 Pass@1: 70.2. Result ID: 69cb96f447f34ce924b44323. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"Discard-All"}. This record does not assert independent reproduction. ### DeepSeek-v3.2 Pass@1: 69.9. Result ID: 69cb96f447f34ce924b44324. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"Keep-Last-N"}. This record does not assert independent reproduction. ### DeepSeek-v3.2 Pass@1: 69.2. Result ID: 69cb96f447f34ce924b44325. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"Summary"}. This record does not assert independent reproduction. ### Gemini-3.0-Pro Pass@1: 66.8. Result ID: 69cb96f447f34ce924b44314. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"w/o CM"}. This record does not assert independent reproduction. ### MiroThinker-v1.5-30B-A3B Pass@1: 66.8. Result ID: 69cb96f447f34ce924b4431c. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"-"}. This record does not assert independent reproduction. ### Claude-4.5-Opus Pass@1: 62.4. Result ID: 69cb96f447f34ce924b44313. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"w/o CM"}. This record does not assert independent reproduction. ### DeepSeek-v3.2 Pass@1: 61.6. Result ID: 69cb96f447f34ce924b44322. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"Baseline (w/o CM)"}. This record does not assert independent reproduction. ### OpenAI-o3 Pass@1: 58.1. Result ID: 69cb96f447f34ce924b44315. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"w/o CM"}. This record does not assert independent reproduction. ### AgentSwing Pass@1: 56.7. Result ID: 69cb96f447f34ce924b4432b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"Tongyi-DR-30B-A3B"}. This record does not assert independent reproduction. ### Tongyi-DR-30B-A3B Pass@1: 53.9. Result ID: 69cb96f447f34ce924b44328. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"Discard-All"}. This record does not assert independent reproduction. ### Tongyi-DR-30B-A3B Pass@1: 50.1. Result ID: 69cb96f447f34ce924b44329. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"Keep-Last-N"}. This record does not assert independent reproduction. ### Tongyi-DR-30B-A3B Pass@1: 49.1. Result ID: 69cb96f447f34ce924b4432a. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"Summary"}. This record does not assert independent reproduction. ### AgentFold-30B-A3B Pass@1: 47.3. Result ID: 69cb96f447f34ce924b4431a. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"-"}. This record does not assert independent reproduction. ### Tongyi-DR-30B-A3B Pass@1: 47.1. Result ID: 69cb96f447f34ce924b44327. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"Baseline (w/o CM)"}. This record does not assert independent reproduction. ### IterResearch-30B-A3B Pass@1: 45.2. Result ID: 69cb96f447f34ce924b44319. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"-"}. This record does not assert independent reproduction. ### AgentFounder-30B-A3B Pass@1: 43.3. Result ID: 69cb96f447f34ce924b4431b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"-"}. This record does not assert independent reproduction. ### OpenAI DeepResearch Pass@1: 42.9. Result ID: 69cb96f447f34ce924b44316. [Reporting paper]() Recorded evaluation configuration: {"Context Management":"-"}. This record does not assert independent reproduction. ### DeepMiner-32B-RL Pass@1: 40.1. Result ID: 69cb96f447f34ce924b44318. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"-"}. This record does not assert independent reproduction. ### AgentSwing Pass@1: 38. Result ID: 69cb96f447f34ce924b44321. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Base Model":"GPT-OSS-120B"}. This record does not assert independent reproduction. ### GPT-OSS-120B Pass@1: 33.6. Result ID: 69cb96f447f34ce924b4431f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"Keep-Last-N"}. This record does not assert independent reproduction. ### GPT-OSS-120B Pass@1: 31.5. Result ID: 69cb96f447f34ce924b4431e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"Discard-All"}. This record does not assert independent reproduction. ### GPT-OSS-120B Pass@1: 30.8. Result ID: 69cb96f447f34ce924b44320. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"Summary"}. This record does not assert independent reproduction. ### GPT-OSS-120B Pass@1: 28.4. Result ID: 69cb96f447f34ce924b4431d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"Baseline (w/o CM)"}. This record does not assert independent reproduction. ### ASearcher-Web-32B Pass@1: 15.6. Result ID: 69cb96f447f34ce924b44317. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Context Management":"-"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.