# General AI Assistant Reasoning on GAIA Source: [General AI Assistant Reasoning on GAIA]() Collection index: [llms.txt]() Data updated: 2026-03-10T09:02:17.085Z Evaluation of General AI Assistant Reasoning capabilities on the base GAIA dataset, measured using 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) | GAIA | | 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 | 67.4 | Not recorded | 69afa56f2d603e6de3e4394d | | MIRO-30B + WEDAS | 66.99 | Not recorded | 69afa56f2d603e6de3e4394d | | MIRO-30B + MIROFLOW | 63.11 | Not recorded | 69afa56f2d603e6de3e4394d | | GPT-5-MINI + WEDAS | 57.28 | Not recorded | 69afa56f2d603e6de3e4394d | | WEBSAILOR-72B | 55.4 | Not recorded | 69afa56f2d603e6de3e4394d | | WEBSAILOR-32B | 53.2 | Not recorded | 69afa56f2d603e6de3e4394d | | ASEARCHER-WEB-32B | 52.8 | Not recorded | 69afa56f2d603e6de3e4394d | | WEBDANCER-QWQ-32B | 51.5 | Not recorded | 69afa56f2d603e6de3e4394d | | GPT-5-MINI + MIROFLOW | 51.46 | Not recorded | 69afa56f2d603e6de3e4394d | | WEBTHINKER-32B-RL | 48.5 | Not recorded | 69afa56f2d603e6de3e4394d | | SEARCH-O1-32B | 39.8 | Not recorded | 69afa56f2d603e6de3e4394d | | O4-MINI | 33.3 | Not recorded | 69afa56f2d603e6de3e4394d | | GPT-4.1 | 22.3 | Not recorded | 69afa56f2d603e6de3e4394d | | QWQ-32B | 22.3 | Not recorded | 69afa56f2d603e6de3e4394d | | GPT-4O | 17.5 | Not recorded | 69afa56f2d603e6de3e4394d | | QWEN-2.5-72B | 14.6 | Not recorded | 69afa56f2d603e6de3e4394d | | QWEN-2.5-32B | 13.6 | Not recorded | 69afa56f2d603e6de3e4394d | ### OPENAI DEEPRESEARCH Pass@1 Accuracy: 67.4. Result ID: 69afde126dbb7075b958643e. [Reporting paper]() Recorded evaluation configuration: {"Category":"CLOSED-SOURCE"}. This record does not assert independent reproduction. ### MIRO-30B + WEDAS Pass@1 Accuracy: 66.99. Result ID: 69afde126dbb7075b9586448. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### MIRO-30B + MIROFLOW Pass@1 Accuracy: 63.11. Result ID: 69afde126dbb7075b9586447. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### GPT-5-MINI + WEDAS Pass@1 Accuracy: 57.28. Result ID: 69afde126dbb7075b9586446. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### WEBSAILOR-72B Pass@1 Accuracy: 55.4. Result ID: 69afde126dbb7075b9586444. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### WEBSAILOR-32B Pass@1 Accuracy: 53.2. Result ID: 69afde126dbb7075b9586443. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### ASEARCHER-WEB-32B Pass@1 Accuracy: 52.8. Result ID: 69afde126dbb7075b9586441. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### WEBDANCER-QWQ-32B Pass@1 Accuracy: 51.5. Result ID: 69afde126dbb7075b9586442. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### GPT-5-MINI + MIROFLOW Pass@1 Accuracy: 51.46. Result ID: 69afde126dbb7075b9586445. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### WEBTHINKER-32B-RL Pass@1 Accuracy: 48.5. Result ID: 69afde126dbb7075b9586440. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### SEARCH-O1-32B Pass@1 Accuracy: 39.8. Result ID: 69afde126dbb7075b958643f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"OPEN-SOURCE"}. This record does not assert independent reproduction. ### O4-MINI Pass@1 Accuracy: 33.3. Result ID: 69afde126dbb7075b958643d. [Reporting paper]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### GPT-4.1 Pass@1 Accuracy: 22.3. Result ID: 69afde126dbb7075b958643b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### QWQ-32B Pass@1 Accuracy: 22.3. Result ID: 69afde126dbb7075b958643c. [Reporting paper]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### GPT-4O Pass@1 Accuracy: 17.5. Result ID: 69afde126dbb7075b958643a. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### QWEN-2.5-72B Pass@1 Accuracy: 14.6. Result ID: 69afde126dbb7075b9586439. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"DIRECT INFERENCE"}. This record does not assert independent reproduction. ### QWEN-2.5-32B Pass@1 Accuracy: 13.6. Result ID: 69afde126dbb7075b9586438. [Reporting paper]() [Method origin 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.