# Best Open-Weight Decision Model for Self-Hosting > Updated Oct 16, 2026 ยท evidence through Oct 16, 2026. Synthesized from cited community evidence and open benchmarks, not vendor marketing. Canonical page: https://modelmatchbook.com/best/decisions-open Winnow-12B Q8 is the provisional first pick for Best Open-Weight Decision Model for Self-Hosting as of October 16, 2026, while independent task measurements are still limited. It scores 68.89 on JevBench (#8 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 60 and its calibration axis 83, each out of 100. Cygnet (blockbrain, frozen Gemma-4-12B-it) scores within two points, so read the top two as close rather than as a measured gap. Cygnet (blockbrain, frozen Gemma-4-12B-it) is the next-ranked alternative. It scores 68.55 on JevBench (#9 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 55 and its calibration axis 87, each out of 100. [1,2] ## 1. Winnow-12B Q8 https://modelmatchbook.com/models/eldanring/winnow-12b Winnow-12B Q8 scores 68.89 on JevBench (#8 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 60 and its calibration axis 83, each out of 100. **Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [1] ## 2. Cygnet (blockbrain, frozen Gemma-4-12B-it) https://modelmatchbook.com/models/blockbrain/cygnet Cygnet (blockbrain, frozen Gemma-4-12B-it) scores 68.55 on JevBench (#9 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 55 and its calibration axis 87, each out of 100. **Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [2] ## 3. Jev-Omni (akhilaaa3, Gemma-4-12B merged) https://modelmatchbook.com/models/akhilaaa3/jev-omni Jev-Omni (akhilaaa3, Gemma-4-12B merged) scores 67.75 on JevBench (#10 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 56 and its calibration axis 87, each out of 100. **Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [3] ## 4. spark-s1-4b-v6 (Open Spark Jev, abhishek085) https://modelmatchbook.com/models/abhishek-rai/spark-s1-4b-v6 spark-s1-4b-v6 (Open Spark Jev, abhishek085) scores 44.9 on JevBench (#24 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 43 and its calibration axis 65, each out of 100. **Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [4] ## 5. swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) https://modelmatchbook.com/models/blockbrain/swanone swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) scores 43.79 on JevBench (#25 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 56 and its calibration axis 89, each out of 100. **Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [5] ## 6. NInfer Qwen3.8-Flash-Next mixed https://modelmatchbook.com/models/igor-l.-ninfer-contributors/ninfer-qwen3.8-flash-next NInfer Qwen3.8-Flash-Next mixed scores 41.97 on JevBench (#28 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 49 and its calibration axis 90, each out of 100. **Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [6] ## 7. jev-local (Qwen3.5-9B) https://modelmatchbook.com/models/us/jev-local jev-local (Qwen3.5-9B) scores 41.33 on JevBench (#29 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 42 and its calibration axis 73, each out of 100. **Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [7] ## 8. decider-4b v2 (Mapika) https://modelmatchbook.com/models/mapika/decider-4b-v2 decider-4b v2 (Mapika) scores 41.24 on JevBench (#30 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 40 and its calibration axis 90, each out of 100. **Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [8] ## FAQ **What is the best model for Best Open-Weight Decision Model for Self-Hosting?** Winnow-12B Q8 ranks first as of October 16, 2026. Winnow-12B Q8 scores 68.89 on JevBench (#8 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 60 and its calibration axis 83, each out of 100. [1] **What is the best alternative to Winnow-12B Q8?** Cygnet (blockbrain, frozen Gemma-4-12B-it) ranks second. Cygnet (blockbrain, frozen Gemma-4-12B-it) scores 68.55 on JevBench (#9 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 55 and its calibration axis 87, each out of 100. [2] **Can I self-host the top pick for Best Open-Weight Decision Model for Self-Hosting?** Yes. Winnow-12B Q8 is open-weight, so it can run on your own hardware as well as through hosted routes. [1] ## Sources 1. "Within the 114 catalog models matched to this evaluation: Scores 68.89 on JevBench (#8 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 60 and its calibration axis 83, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models) 2. "Within the 114 catalog models matched to this evaluation: Scores 68.55 on JevBench (#9 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 55 and its calibration axis 87, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models) 3. "Within the 114 catalog models matched to this evaluation: Scores 67.75 on JevBench (#10 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 56 and its calibration axis 87, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models) 4. "Within the 114 catalog models matched to this evaluation: Scores 44.9 on JevBench (#24 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 43 and its calibration axis 65, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models) 5. "Within the 114 catalog models matched to this evaluation: Scores 43.79 on JevBench (#25 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 56 and its calibration axis 89, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models) 6. "Within the 114 catalog models matched to this evaluation: Scores 41.97 on JevBench (#28 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 49 and its calibration axis 90, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models) 7. "Within the 114 catalog models matched to this evaluation: Scores 41.33 on JevBench (#29 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 42 and its calibration axis 73, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models) 8. "Within the 114 catalog models matched to this evaluation: Scores 41.24 on JevBench (#30 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 40 and its calibration axis 90, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models)