whatmodel.sh · find the best decision models you can run

Best Decision models for document & agent workflows

A leaderboard of the best Decision models for document & agent workflows. Perplexity Decider v1.1 (27B) is #1 right now, followed by StartLux-Decision v1.1 27B and Mercury Decide (paid endpoint). Published typed-decision evaluations, with evaluator-specific protocols and tested settings retained. Each task score uses only its reviewed benchmarks. Filter by your computer or budget to find the best one you can use.

117 models · 108 benchmarks · updated

Compare tested decision models and inference recipes across text, vision and workflow tasks. Use task filters and raw results: probability consistency measures coherence, not correctness.

Filter by your hardware and budget · reset
ram[2][4][8][16][24][32][48][64][96][128][192][256]
[]
GB
gpu[apple silicon][graphics card][unified memory][none]
price[local][$0.05][$0.1][any]max per M input tokens
Filter by task
task[all tasks][tools & automation][retrieval & classification][language understanding][arts & human taste][knowledge & reasoning][vision][workflows][consistency]

Scores use reviewed workflows evaluations only. Compare scores within this task. Models without task measurements are excluded.

New #1s:
orRSS

detecting your OS…

$ terminal

detecting your OS…

Run curl whatmodel.sh/decisionto get this list in your terminal (add &format=json for agents).

Score vs release date

Release dates available for 27 of 116 models. Undated models are omitted; month-only dates are plotted at the start of the month.

#modeltask score↓where↓RAM↓speed↓get itsources
#modeltask score↓where↓RAM↓speed↓get itsources
1Perplexity Decider v1.1 (27B) Perplexity80±1api price unknownopenrouter.ai ↗DecisionPivot · StartLux LabsLeanMCP · JevBench
2StartLux-Decision v1.1 27B StartLux74±3model files ↗huggingface.co ↗JevalKit (Valen Team)
3Mercury Decide (paid endpoint) Inception72±3api price unknownopenrouter.ai ↗LeanMCP · JevBenchPerch benchmark results
4StartLux-Decision v1.1 9B StartLux68±3model files ↗huggingface.co ↗JevalKit (Valen Team)
5Quyet-1.0-Large chinhnc67±5*model files ↗huggingface.co ↗DecideBench (Cho Yin Yong)
6StartLux-Decision v1.1 4B StartLux67±3model files ↗huggingface.co ↗JevalKit (Valen Team)
7bosun-v3.1-1.7b (DecisionBench 2ef2d972) Hanno Labs67±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
8Microsoft-Decision-1 Microsoft66±2api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Perch benchmark results
9Jev 1.13 TypeSafe65±1api $0.042/M input tokensdocs.typesafe.ai ↗Hanno Labs DecisionBench v1 reviewed resultsDecisionPivot · StartLux LabsLeanMCP · JevBenchTyped Decision Models under Prevalence Shift: Decision Training, Calibration, and Implicit PriorsSystem One Bench (Ali Alhashimi)DecisionModelHub · support benchmarks+3
10bosun-v3.1-0.6b (DecisionBench aaa9dd06) Hanno Labs64±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
11baselabs mammoth-1 (27B) baselabs64±4*model files ↗huggingface.co ↗System One Bench (Ali Alhashimi)
12GPT-6 Luna Decisions OpenAI64±2api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)DecisionModelHub · support benchmarksDecideBench (Cho Yin Yong)Perch benchmark results
13reflex-27b (DecisionBench 1d4bf0f2) kshetrajna1263±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
14Perplexity Decider v1.2 (27B) Perplexity63±4*model files ↗huggingface.co ↗System One Bench (Ali Alhashimi)
15Jev 1.14 TypeSafe63±2api $0.042/M input tokensdocs.typesafe.ai ↗JevalKit (Valen Team)System One Bench (Ali Alhashimi)
16Nace.AI Drex v2.0 (35B-A3B) Nace.AI63±3model files ↗huggingface.co ↗System One Bench (Ali Alhashimi)DecideBench (Cho Yin Yong)
17d1-ultra Liquid AI63±4*api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)
18d1 (hosted) Liquid AI62±2api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)Perch benchmark results
19baselabs elephant-1 (9B) baselabs62±4*model files ↗huggingface.co ↗System One Bench (Ali Alhashimi)
20imajev-4b (DecisionBench 712891d1) mohit6789062±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
21litjev (DecisionBench 1d4bf0f2) zhengxuyu62±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
22glm-5.3-flash (DecisionBench openrout) Z.ai61±2†comparison onlyHanno Labs DecisionBench v1 reviewed results
23reflex-qwen3.5-4b-lora (DecisionBench 9df1cbbb) kshetrajna1261±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
24Clef Cloudflare61±1api $0.24/M input tokens +local~68GBdevelopers.cloudflare.com ↗DecisionPivot · StartLux LabsLeanMCP · JevBenchSystem One Bench (Ali Alhashimi)DecisionModelHub · support benchmarksDecideBench (Cho Yin Yong)
25imajev-4b (DecisionBench c9e5f132) mohit6789061±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
26Nace.AI Drex Max v1 (27B) Nace-Deepinfra61±4*model files ↗huggingface.co ↗System One Bench (Ali Alhashimi)
27Perplexity Decider Flash v1.2 (4B) Perplexity61±2local~10GBhow to run › Ollaya · original runsSystem One Bench (Ali Alhashimi)
28StartLux-Decision v1.1 2B StartLux61±2model files ↗huggingface.co ↗JevalKit (Valen Team)
29decider-35b-a3b (DecisionBench d9783c58) Mapika61±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
30openjev-sglang (DecisionBench 1355db6a) ekzhang60±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
31Span-02 (Gemma 4 26B-A4B) Respan60±4*api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)
32xor (DecisionBench 679decd4) juspay60±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
33d1.1 (hosted) Liquid AI60±4*api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)
34gpt-5.6-luna (DecisionBench openrout) OpenAI60±2†comparison onlyHanno Labs DecisionBench v1 reviewed results
35simplejev-qwen3.8-27b (DecisionBench 1d4bf0f2) featherless-ai59±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
36Mercury Decide (free endpoint) Inception59±4*api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)
37deepseek-v4.1-flash (DecisionBench openrout) DeepSeek59±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
38Solar Decide Upstage59±3api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)
39Winnow-12B (DecisionBench b6ac22b0) EldanRing58±1local~16GBhow to run › Hanno Labs DecisionBench v1 reviewed resultsOllaya · original runs
40simplejev-qwen3.6-35b-a3b (DecisionBench 995ad96e) featherless-ai58±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
41vLLM-SR d3-flash (9B) vLLM Semantic Router58±2local~18GBhow to run › Ollaya · original runs
42jqv (DecisionBench 9216db57) Octalab-Inc58±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
43Nace.AI Drex v1.5 Nace.AI57±2model files ↗huggingface.co ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)DecideBench (Cho Yin Yong)
44openjev (DecisionBench ec4ff3df) razorback1657±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
45vLLM-SR d3-mini (4B) vLLM Semantic Router57±2local~11GBhow to run › Ollaya · original runs
46Jebadiah 27B v2.1 (Ollaya Q4_K_M) frontier-infra57±4local~16GBhow to run › Ollaya · original runs
47StartLux-Decision v1.1 0.8B StartLux57±2model files ↗huggingface.co ↗JevalKit (Valen Team)
48Jebadiah 9B v2.1 (Ollaya Q8_0) frontier-infra57±4local~9.1GBhow to run › Ollaya · original runs
49Open-Jev-9B (DecisionBench 47e96688) ZefanCai56±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
50Together Tev1 Qwen3.5-4B Together56±3model files ↗huggingface.co ↗System One Bench (Ali Alhashimi)DecideBench (Cho Yin Yong)
51djev-dev (DecisionBench f7f5b7f5) Davipar56±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
52open-alternative-jev (DecisionBench 4a85df18) IkerMoel56±2†source code ↗github.com ↗Hanno Labs DecisionBench v1 reviewed results
53Tev1-4B-experimental (DecisionBench 0b7becf0) Together56±2model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed resultsTyped Decision Models under Prevalence Shift: Decision Training, Calibration, and Implicit Priors
54kev-4b (DecisionBench 485ace87) Jared Palmer56±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
55kev-8b (DecisionBench c80773da) Jared Palmer56±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
56JevK5 v0.3 alibiserikbay55±2model files ↗huggingface.co ↗JevalKit (Valen Team)DecideBench (Cho Yin Yong)
57Decider 4B Mapika55±2local~11GBhow to run › Ollaya · original runs
58Bespoke-Nimble-9B (DecisionBench 594dfdcf) Bespoke Labs55±1model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed resultsTyped Decision Models under Prevalence Shift: Decision Training, Calibration, and Implicit Priors
59vLLM-SR Decision 2.0 Nox 4B vLLM Semantic Router54±2local~12GBhow to run › Ollaya · original runs
60SemIf (DecisionBench 1f2dea3e) TheoLeeCJ54±2†source code ↗github.com ↗Hanno Labs DecisionBench v1 reviewed results
61vLLM-SR Decision 2.0 Lux 9B vLLM Semantic Router54±2local~20GBhow to run › Ollaya · original runs
62InternLM Intern-Decision Qwen3.5-4B Shanghai AI Laboratory (InternLM)54±2model files ↗huggingface.co ↗JevalKit (Valen Team)FloorIsAwake · Privacy Decision Benchmark
63decider-2b (DecisionBench fa996cea) Mapika54±2model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed resultsChao Ma · independent injection study
64cua-s1-4b-0.2 (DecisionBench 16818868) cua-ai54±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
65Jebadiah 4B v2 (Ollaya Q8_0) frontier-infra54±2local~5.5GBhow to run › Ollaya · original runs
66Kev 4B r10 Jared Palmer54±1local~11GBhow to run › Ollaya · original runsJevalKit (Valen Team)System One Bench (Ali Alhashimi)
67LiquidAI d1-3B Liquid AI53±2model files ↗huggingface.co ↗JevalKit (Valen Team)System One Bench (Ali Alhashimi)
68Clef-flash Cloudflare53±1api $0.038/M input tokens +local~25GBdevelopers.cloudflare.com ↗DecisionPivot · StartLux LabsLeanMCP · JevBenchOllaya · original runsJevalKit (Valen Team)DecisionModelHub · support benchmarksSystem One Bench (Ali Alhashimi)+1
69Bespoke Nimble 9B v3 Bespoke Labs52±2local~21GBhow to run › Ollaya · original runs
70Solar Decide Flash Upstage52±2api price unknownopenrouter.ai ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)
71Bespoke Nimble 9B v2 Bespoke Labs52±2local~20GBhow to run › Ollaya · original runs
72Span-01 Pro Respan52±9api price unknownwww.respan.ai ↗Perch benchmark results
73Clef-omni Cloudflare52±2api $0.15/M input tokens +local~87GBdevelopers.cloudflare.com ↗LeanMCP · JevBenchSystem One Bench (Ali Alhashimi)
74baselabs joey-1 (2B) baselabs52±4*api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)
75vLLM-SR d3-nano (2B) vLLM Semantic Router52±2local~8.2GBhow to run › Ollaya · original runsSystem One Bench (Ali Alhashimi)
76ZTC-Judge-9B (DecisionBench 05d154a5) FINAL-Bench52±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
77djev-spark (DecisionBench 1444f3e9) mmastrac52±2†source code ↗github.com ↗Hanno Labs DecisionBench v1 reviewed results
78zerank-2-reranker (DecisionBench 5eae30d5) zeroentropy50±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
79GLiClass v4 edge (0.4B) Knowledgator Engineering49±2local~2.7GBhow to run › Ollaya · original runs
80Open-Jev-2B (DecisionBench 0c7aa498) ZefanCai49±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
81InternLM Intern-Decision Qwen3.5-2B Shanghai AI Laboratory (InternLM)49±2model files ↗huggingface.co ↗JevalKit (Valen Team)FloorIsAwake · Privacy Decision Benchmark
82vLLM-SR Decision 2.0 Sol 2B vLLM Semantic Router46±2local~11GBhow to run › Ollaya · original runs
83vLLM-SR d3-lite (0.8B) vLLM Semantic Router45±2local~4.5GBhow to run › Ollaya · original runsSystem One Bench (Ali Alhashimi)
84LiquidAI d1-omni-600M Liquid AI45±2local~2.7GBhow to run › Ollaya · original runsSystem One Bench (Ali Alhashimi)
85InternLM Intern-Decision Qwen3.5-0.8B Shanghai AI Laboratory (InternLM)44±2model files ↗huggingface.co ↗JevalKit (Valen Team)FloorIsAwake · Privacy Decision Benchmark
86Decision-1.0-Eos-0.8B (DecisionBench 3c2d6326) llm-semantic-router44±1local~5.8GBhow to run › Hanno Labs DecisionBench v1 reviewed resultsOllaya · original runs
87vLLM-SR Decision 2.0 Eos 0.8B vLLM Semantic Router44±2local~5.8GBhow to run › Ollaya · original runs
88vLLM-SR Decision 2.0 Kai 0.6B vLLM Semantic Router43±2local~3.7GBhow to run › Ollaya · original runs
89Qwen3-Reranker-4B (DecisionBench 22e68366) Alibaba (Qwen)42±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
90Kev 0.8B r15 Jared Palmer41±2local~4.6GBhow to run › Ollaya · original runsSystem One Bench (Ali Alhashimi)
91GLiNER2.5-Decide Fastino40±9model files ↗huggingface.co ↗Perch benchmark results
92vLLM-SR d3-edge (0.6B) vLLM Semantic Router40±2local~2.6GBhow to run › Ollaya · original runsSystem One Bench (Ali Alhashimi)
93kev-0.6b (DecisionBench dece6dba) Jared Palmer39±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
94mojev (DecisionBench 0c8695b6) MoLeMo-Lab38±2†request access ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
95smalljev-semantic-v9 (DecisionBench 8e2bac7c) isHeSatoshi37±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
96OpenDecision (DecisionBench a51e07b5) deepanwadhwa31±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
97GLiNER2.5-Decide (DecisionBench 0872ab14) Fastino31±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
98laya-typed-decisions (DecisionBench bc76315b) ConvAI Innovations30±1model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed resultsFloorIsAwake · Privacy Decision Benchmark
99ZTC-Judge-4B (DecisionBench b0bb1603) FINAL-Bench30±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
100mxbai-rerank-base-v2 (DecisionBench 3ea9d4df) mixedbread-ai29±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
101open-jev-deberta-v3-large (DecisionBench 19bf9a64) com-kotobalabs29±2model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed resultsChao Ma · independent injection study
102gliner2-large-v1 (DecisionBench f32ea6ef) Fastino28±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
103rlcd-modernbert-151m (DecisionBench 8af2496e) heman10x28±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
104laya (DecisionBench 1c5edc17) ConvAI Innovations27±1local~1.7GBhow to run › Hanno Labs DecisionBench v1 reviewed resultsOllaya · original runs
105kev-0.5b (DecisionBench 9ce2fd39) Jared Palmer26±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
106gliner2.5-small-v1 (DecisionBench 7e6f537f) Fastino24±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
107gliner2.5-base-v1 (DecisionBench 1a8bc24e) Fastino22±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
108gliner2.5-multi-v1 (DecisionBench a221b77a) Fastino22±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
109NanoJev (DecisionBench 4a19595e) C-Tianyu21±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
110bge-reranker-v2-m3 (DecisionBench 953dc6f6) BAAI20±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
111KaLM-Reranker-V1-Small-R2 (DecisionBench d1c8fdf9) KaLM-Embedding19±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
112KaLM-Reranker-V1-Nano-R2 (DecisionBench 3902d645) KaLM-Embedding19±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
113CLM-v0.1-8B Qwen3-8B heads Contrastive-LM15±2local~15GBhow to run › Ollaya · original runsDecideBench (Cho Yin Yong)Perch benchmark results
114certo-decision-model (DecisionBench 7628c0da) altslate9±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
115gte-reranker-modernbert-base (DecisionBench f7481e60) Alibaba9±2†model files ↗huggingface.co ↗Hanno Labs DecisionBench v1 reviewed results
116Supersonic Labs Julia 1 Supersonic Labs9±3*model files ↗huggingface.co ↗DecideBench (Cho Yin Yong)
—Bespoke Nimble v4 Max (27B) Bespoke Labsnot scored yetmodel files ↗huggingface.co ↗

Includes 2 comparison-only models with no verified API or download · hide them

117 of 117 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † no independently run results verified · ~RAM is estimated; full context may need more memory

117 models · 108 benchmarks · updated