# Best Decision Model for Agent Routing and Scoring

> Updated Oct 16, 2026 · evidence through Oct 16, 2026. Synthesized from cited community evidence and open benchmarks, not vendor marketing. Canonical page: https://modelmatchbook.com/best/decisions

Sage 1.3.0 (Levanto Labs) is the provisional first pick for Best Decision Model for Agent Routing and Scoring as of October 16, 2026, while independent task measurements are still limited. Sage 1.3.0 leads the JevBench composite ranking with the highest overall score of 74.05, combining strong calibration (92) with moderate decision accuracy (66). H2O-Lightning-4B v1.1 (H2O.ai, Qwen3.5-4B fine-tune, stock vLLM + open shim) is the next-ranked alternative. It scores 72.52 on JevBench (#2 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 90, each out of 100. [1,2]

## 1. Sage 1.3.0 (Levanto Labs)
https://modelmatchbook.com/models/levanto-labs/sage-1.3.0

Sage 1.3.0 leads the JevBench composite ranking with the highest overall score of 74.05, combining strong calibration (92) with moderate decision accuracy (66).

**Best when:** Use for agent routing where calibrated confidence matters, as it scores 92 on JevBench's calibration axis. [1]

## 2. H2O-Lightning-4B v1.1 (H2O.ai, Qwen3.5-4B fine-tune, stock vLLM + open shim)
https://modelmatchbook.com/models/h2oai/h2o-lightning-4b

H2O-Lightning-4B v1.1 (H2O.ai, Qwen3.5-4B fine-tune, stock vLLM + open shim) scores 72.52 on JevBench (#2 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 90, each out of 100.

**Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [2]

## 3. Jev 1.13.0 (TypeSafe AI)
https://modelmatchbook.com/models/typesafe-ai/jev-1.13.0

Jev 1.13.0 places third on JevBench with 71.49 composite, and independent evaluation shows 0.028 pooled ECE across 22 choice datasets with substantial variance (0.003 to 0.279) and under-confidence on yes/no tasks.

**Best when:** Filter to its most confident half of predictions to boost accuracy dramatically, for example from 79.7% to 96.3% on Banking77. [4]

**Watch out for:**
- Watch for variable calibration across datasets, with ECE ranging from 0.003 to 0.279, and slight under-confidence on binary yes/no decisions. [4]

## 4. Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)
https://modelmatchbook.com/models/chinhnc/quyet-1.0-large

Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits) scores 71.39 on JevBench (#4 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 73 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. [5]

## 5. wity-1 (Wity, reasoning auto)
https://modelmatchbook.com/models/wity/wity-1

wity-1 (Wity, reasoning auto) scores 70.77 on JevBench (#5 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 70 and its calibration axis 88, each out of 100.

**Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [6]

## 6. decider-12b v2 (Mapika)
https://modelmatchbook.com/models/mapika/decider-12b

decider-12b v2 (Mapika) scores 70.42 on JevBench (#6 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 61 and its calibration axis 84, each out of 100.

**Best when:** Its strongest result for this task is on JevBench, which measures calibrated typed decisions. [7]

## 7. torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout)
https://modelmatchbook.com/models/torchcast-ai/torchcast-decision-12b

torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) scores 69.91 on JevBench (#7 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 61 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. [8]

## 8. 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. [3]

## FAQ

**What is the best model for Best Decision Model for Agent Routing and Scoring?**

Sage 1.3.0 (Levanto Labs) ranks first as of October 16, 2026. Sage 1.3.0 leads the JevBench composite ranking with the highest overall score of 74.05, combining strong calibration (92) with moderate decision accuracy (66). [1]

**What is the best alternative to Sage 1.3.0 (Levanto Labs)?**

H2O-Lightning-4B v1.1 (H2O.ai, Qwen3.5-4B fine-tune, stock vLLM + open shim) ranks second. H2O-Lightning-4B v1.1 (H2O.ai, Qwen3.5-4B fine-tune, stock vLLM + open shim) scores 72.52 on JevBench (#2 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 90, each out of 100. [2]

**Which open-weight model ranks highest for Best Decision Model for Agent Routing and Scoring?**

Winnow-12B Q8 is the highest-ranked open-weight model, at #8. 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. [3]

## Sources
1. "Within the 114 catalog models matched to this evaluation: Scores 74.05 on JevBench (#1 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 66 and its calibration axis 92, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models)
2. "Within the 114 catalog models matched to this evaluation: Scores 72.52 on JevBench (#2 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 90, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models)
3. "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)
4. "Two outside sources on Jev, and what they mean for this measurement. Neither is TypeSafe material. - An evaluation paper (Deußer, Sparrenberg and Sifa, arXiv 2609.37647) tested jev-1.13.0 on 37 datasets. Pooled calibration error (ECE) over 22 choice datasets is 0.028, but it is from 0.003 to 0.279 for single datasets. Yes/no answers are slightly under-confident. When Jev answers only its most confident half, accuracy rises, for example Banking77 from 79.7% to 96.3%. - A third-party explainer…" (mohanraj00, https://github.com/mohanraj00/groundgate/issues/67#issuecomment-5976010361)
5. "Within the 114 catalog models matched to this evaluation: Scores 71.39 on JevBench (#4 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 73 and its calibration axis 90, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models)
6. "Within the 114 catalog models matched to this evaluation: Scores 70.77 on JevBench (#5 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 70 and its calibration axis 88, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models)
7. "Within the 114 catalog models matched to this evaluation: Scores 70.42 on JevBench (#6 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 61 and its calibration axis 84, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models)
8. "Within the 114 catalog models matched to this evaluation: Scores 69.91 on JevBench (#7 of 114), Benchmark Heaven's composite of decision accuracy, calibration, speed, and cost for typed decision models; its decision accuracy axis is 61 and its calibration axis 83, each out of 100." (JevBench, https://benchmarkheaven.com/jev-models)