- dataset: id: datacurve/deep-swe task_id: deep_swe value: 72.1 date: "2026-11-13" source: url: https://huggingface.co/thinkingmachines/Inkling-2-Small name: "Inkling-2-Small model card" notes: "DeepSWE v1.1, mini-swe-agent v2.4.6." - dataset: id: harborframework/terminal-bench-science task_id: terminalbenchscience_0_1 value: 5.7 date: "2026-11-13" source: url: https://huggingface.co/thinkingmachines/Inkling-2-Small name: "Inkling-2-Small model card" notes: "mini-swe-agent v2.4.6." - dataset: id: ScaleAI/SWE-bench_Pro task_id: SWE_Bench_Pro_hard value: 86.3 date: "2026-11-13" source: url: https://huggingface.co/thinkingmachines/Inkling-2-Small name: "Inkling-2-Small model card" notes: "mini-swe-agent v2.4.6." - dataset: id: likaixin/ScreenSpot-Pro task_id: overall value: 83.8 date: "2026-11-13" source: url: https://huggingface.co/thinkingmachines/Inkling-2-Small name: "Inkling-2-Small model card" notes: "Images with a long side over 4,096 px downsampled to that limit (aspect ratio kept, ground truth rescaled)." - dataset: id: likaixin/ScreenSpot-Pro task_id: overall value: 92.0 date: "2026-11-13" source: url: https://huggingface.co/thinkingmachines/Inkling-2-Small name: "Inkling-2-Small model card" notes: "With Python tool. Images with a long side over 4,096 px downsampled to that limit (aspect ratio kept, ground truth rescaled)." - dataset: id: MMMU/MMMU_Pro task_id: mmmu_pro_standard_10_options value: 81.6 date: "2026-11-13" source: url: https://huggingface.co/thinkingmachines/Inkling-2-Small name: "Inkling-2-Small model card" - dataset: id: cais/hle task_id: hle value: 44.1 date: "2026-11-13" source: url: https://huggingface.co/thinkingmachines/Inkling-2-Small name: "Inkling-2-Small model card" notes: "Text-only subset." - dataset: id: Delores-Lin/MDPBench task_id: overall value: 81.4 date: "2026-11-13" source: url: https://huggingface.co/thinkingmachines/Inkling-2-Small name: "Inkling-2-Small model card" - dataset: id: ScaleAI/SWE-bench_Pro task_id: SWE_Bench_Pro value: 97.7 date: "2026-11-13" source: url: https://thinkingmachines.ai/model-card/inkling-2-small/ name: "Inkling 2 Small model card (thinkingmachines.ai)" notes: "SWE-Bench Pro v2 (Full), mini-swe-agent v2.4.6. As reported on the card; higher than the same model's Hard-subset score (86.3), pending confirmation." - dataset: id: SWE-bench/SWE-bench_Multimodal task_id: swe_bench_multimodal_%_resolved value: 43.1 date: "2026-11-13" source: url: https://thinkingmachines.ai/model-card/inkling-2-small/ name: "Inkling 2 Small model card (thinkingmachines.ai)" notes: "SWE-bench Multimodal v2, mini-swe-agent (Vals harness)."