- dataset: id: SWE-bench/SWE-bench_Verified task_id: swe_bench_%_resolved value: 76.2 date: "2026-08-07" source: url: https://arxiv.org/abs/2608.09119 name: "Motif 3 Technical Report — Table 6" - dataset: id: Idavidrein/gpqa task_id: diamond value: 83.4 date: "2026-08-07" source: url: https://arxiv.org/abs/2608.09119 name: "Motif 3 Technical Report — Table 6" - dataset: id: cais/hle task_id: hle value: 37.0 date: "2026-08-07" source: url: https://arxiv.org/abs/2608.09119 name: "Motif 3 Technical Report — Table 6"