# General AI Assistant Reasoning on BrowseComp Source: [General AI Assistant Reasoning on BrowseComp]() Collection index: [llms.txt]() Data updated: 2026-03-10T09:02:17.023Z Evaluation of general reasoning capabilities for AI assistants using the BrowseComp dataset, measured by pass@1 accuracy. 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 | General AI Assistant Reasoning | | Dataset (including any stated split) | BrowseComp (BC) | | Metric | Pass@1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 17 of 17 | | 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 Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pass@1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | OPENAI DEEPRESEARCH | 51.5 | Not recorded | 69afa56f2d603e6de3e4394d | | MIRO-30B + WEDAS | 26 | Not recorded | 69afa56f2d603e6de3e4394d | | GPT-5-MINI + WEDAS | 17 | Not recorded | 69afa56f2d603e6de3e4394d | | MIRO-30B + MIROFLOW | 17 | Not recorded | 69afa56f2d603e6de3e4394d | | GPT-5-MINI + MIROFLOW | 15 | Not recorded | 69afa56f2d603e6de3e4394d | | WEBSAILOR-72B | 12 | Not recorded | 69afa56f2d603e6de3e4394d | | WEBSAILOR-32B | 10.5 | Not recorded | 69afa56f2d603e6de3e4394d | | O4-MINI | 6.1 | Not recorded | 69afa56f2d603e6de3e4394d | | ASEARCHER-WEB-32B | 5.2 | Not recorded | 69afa56f2d603e6de3e4394d | | WEBDANCER-QWQ-32B | 3.8 | Not recorded | 69afa56f2d603e6de3e4394d | | SEARCH-O1-32B | 2.8 | Not recorded | 69afa56f2d603e6de3e4394d | | WEBTHINKER-32B-RL | 2.8 | Not recorded | 69afa56f2d603e6de3e4394d | | GPT-4.1 | 1.5 | Not recorded | 69afa56f2d603e6de3e4394d | | QWEN-2.5-32B | 0.6 | Not recorded | 69afa56f2d603e6de3e4394d | | QWEN-2.5-72B | 0.6 | Not recorded | 69afa56f2d603e6de3e4394d | | GPT-4O | 0.6 | Not recorded | 69afa56f2d603e6de3e4394d | | QWQ-32B | 0.5 | Not recorded | 69afa56f2d603e6de3e4394d | ### OPENAI DEEPRESEARCH Pass@1 Accuracy: 51.5. Result ID: 69afde126dbb7075b958641a. [Reporting paper]() Recorded evaluation configuration: {"Category":"CLOSED-SOURCE"}. This record does not assert independent reproduction. ### MIRO-30B + WEDAS Pass@1 Accuracy: 26. Result ID: 69afde126dbb7075b9586424. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### GPT-5-MINI + WEDAS Pass@1 Accuracy: 17. Result ID: 69afde126dbb7075b9586422. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### MIRO-30B + MIROFLOW Pass@1 Accuracy: 17. Result ID: 69afde126dbb7075b9586423. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### GPT-5-MINI + MIROFLOW Pass@1 Accuracy: 15. Result ID: 69afde126dbb7075b9586421. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### WEBSAILOR-72B Pass@1 Accuracy: 12. Result ID: 69afde126dbb7075b9586420. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### WEBSAILOR-32B Pass@1 Accuracy: 10.5. Result ID: 69afde126dbb7075b958641f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### O4-MINI Pass@1 Accuracy: 6.1. Result ID: 69afde126dbb7075b9586419. [Reporting paper]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### ASEARCHER-WEB-32B Pass@1 Accuracy: 5.2. Result ID: 69afde126dbb7075b958641d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### WEBDANCER-QWQ-32B Pass@1 Accuracy: 3.8. Result ID: 69afde126dbb7075b958641e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### SEARCH-O1-32B Pass@1 Accuracy: 2.8. Result ID: 69afde126dbb7075b958641b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### WEBTHINKER-32B-RL Pass@1 Accuracy: 2.8. Result ID: 69afde126dbb7075b958641c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### GPT-4.1 Pass@1 Accuracy: 1.5. Result ID: 69afde126dbb7075b9586417. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### QWEN-2.5-32B Pass@1 Accuracy: 0.6. Result ID: 69afde126dbb7075b9586414. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### QWEN-2.5-72B Pass@1 Accuracy: 0.6. Result ID: 69afde126dbb7075b9586415. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### GPT-4O Pass@1 Accuracy: 0.6. Result ID: 69afde126dbb7075b9586416. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### QWQ-32B Pass@1 Accuracy: 0.5. Result ID: 69afde126dbb7075b9586418. [Reporting paper]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.