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

Best Decision models for images & screens

A leaderboard of the best Decision models for images & screens. d1-ultra is #1 right now, followed by d1.1 (hosted) and Jev 1.13. 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.

79 models · 21 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 vision 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 24 of 79 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
1d1-ultra Liquid AI75±4api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarks
2d1.1 (hosted) Liquid AI74±4api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarks
3Jev 1.13 TypeSafe74±4api $0.042/M input tokensdocs.typesafe.ai ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarksBenchmark Heaven (own decision evaluations)
4Perplexity Decider v1.2 (27B) Perplexity72±3model files ↗huggingface.co ↗System One Bench (Ali Alhashimi)Decision Index Vision 0.4Etsabary · decision benchmarks
5Jev 1.14 TypeSafe71±4api $0.042/M input tokensdocs.typesafe.ai ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarksJevalKit (Valen Team)Benchmark Heaven (own decision evaluations)
6Mercury Decide (free endpoint) Inception70±4api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)
7Amos 1 Large (27B) mukaddamzaid69±4model files ↗huggingface.co ↗Decision Index Vision 0.4Etsabary · decision benchmarks
8Clef Cloudflare69±4api $0.24/M input tokens +local~68GBdevelopers.cloudflare.com ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarksBenchmark Heaven (own decision evaluations)
9Mercury Decide (paid endpoint) Inception68±7*api price unknownopenrouter.ai ↗Etsabary · decision benchmarks
10vLLM-SR d3-ultra (Decision 3.0, 27B) vLLM Semantic Router66±4model files ↗huggingface.co ↗Decision Index Vision 0.4Etsabary · decision benchmarks
11WeMM-JEV-27B Rover0065±5model files ↗huggingface.co ↗Decision Index Vision 0.4
12RBDash-Decision v0.2 RBDash-Team64±5model files ↗huggingface.co ↗Decision Index Vision 0.4
13d1 (hosted) Liquid AI64±7*api price unknownopenrouter.ai ↗Etsabary · decision benchmarks
14Clef-flash Cloudflare64±3api $0.038/M input tokens +local~25GBdevelopers.cloudflare.com ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarksJevalKit (Valen Team)Benchmark Heaven (own decision evaluations)
15Fastino GLiDE 1.2 Fastino63±5model files ↗huggingface.co ↗Decision Index Vision 0.4
16vLLM-SR d3-turbo v1.1 (27B) vLLM Semantic Router63±5model files ↗huggingface.co ↗Decision Index Vision 0.4
17Span-02 (Gemma 4 26B-A4B) Respan63±3api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)Decision Index Vision 0.4
18H2O Lightning 31B H2O.ai63±5request access ↗huggingface.co ↗Decision Index Vision 0.4
19VisionJEV 1.0.0 (27B) taoszhang63±5model files ↗huggingface.co ↗Decision Index Vision 0.4
20AutoTrust-JEV-27B v1.1 AutoTrust AI Lab62±5model files ↗huggingface.co ↗Decision Index Vision 0.4
21Perplexity Decider Flash v1.2 (4B) Perplexity62±3local~10GBhow to run › System One Bench (Ali Alhashimi)Decision Index Vision 0.4Etsabary · decision benchmarks
22StartLux-Decision v1.1 27B StartLux62±5model files ↗huggingface.co ↗Decision Index Vision 0.4JevalKit (Valen Team)
23Nace.AI Drex Max v1 (27B) Nace-Deepinfra61±5model files ↗huggingface.co ↗Decision Index Vision 0.4
24vLLM-SR d3 (27B) vLLM Semantic Router61±5model files ↗huggingface.co ↗Decision Index Vision 0.4
25Herbert v0.5 leinenterprises61±5model files ↗huggingface.co ↗Decision Index Vision 0.4
26OneJev1.5-27B OmniJev60±5model files ↗huggingface.co ↗Decision Index Vision 0.4
27Aleria Judge 1.1.0 (Gemma 4 31B) (decision readout) Decision Index submission: aleria-judge-1.1.060±5source code ↗github.com ↗Decision Index Vision 0.4
28JEV-27B-VL AutoTrust AI Lab59±5model files ↗huggingface.co ↗Decision Index Vision 0.4
29jev-vision-27b e12ex259±5model files ↗huggingface.co ↗Decision Index Vision 0.4
30KnowLine 35B-A3B Gen1 PelaAI58±5model files ↗huggingface.co ↗Decision Index Vision 0.4
31GPT-6 Luna Decisions OpenAI58±3api price unknownopenrouter.ai ↗System One Bench (Ali Alhashimi)Etsabary · decision benchmarks
32Sieve-Vision-27B Sthānika AI57±5model files ↗huggingface.co ↗Decision Index Vision 0.4
33StartLux-Decision v1.1 9B StartLux56±11*model files ↗huggingface.co ↗JevalKit (Valen Team)
34Xor 1.2 Juspay Technologies55±5model files ↗huggingface.co ↗Decision Index Vision 0.4
35vLLM-SR d3-flash (9B) vLLM Semantic Router55±5local~18GBhow to run › Decision Index Vision 0.4
36OneJev1.5-9B OmniJev54±5model files ↗huggingface.co ↗Decision Index Vision 0.4
37StartLux-Decision v1.1 4B StartLux54±11*model files ↗huggingface.co ↗JevalKit (Valen Team)
38RSI-Jev v6.1 VL 27B (effort auto) shgao53±5model files ↗huggingface.co ↗Decision Index Vision 0.4
39jev-d3-46k tinnel12351±5model files ↗huggingface.co ↗Decision Index Vision 0.4
40vLLM-SR d3-mini (4B) vLLM Semantic Router51±5local~11GBhow to run › Decision Index Vision 0.4
41Solomon v1.1 Doccy Health51±5model files ↗huggingface.co ↗Decision Index Vision 0.4
42JPT-9B Qwen3.5-9B LoRA kirp49±5model files ↗huggingface.co ↗Decision Index Vision 0.4Benchmark Heaven (own decision evaluations)
43matilda-jev-v1.5 (27B) Maincode49±5model files ↗huggingface.co ↗Decision Index Vision 0.4
44LiquidAI d1-3B Liquid AI48±10model files ↗huggingface.co ↗JevalKit (Valen Team)Benchmark Heaven (own decision evaluations)
45Surogate Rune 26B-A4B v3 Surogate48±5request access ↗huggingface.co ↗Decision Index Vision 0.4Benchmark Heaven (own decision evaluations)
46Sieve-Vision-4B Sthānika AI47±5model files ↗huggingface.co ↗Decision Index Vision 0.4
47xor-26b-a4b-v1.1 Juspay Technologies47±5model files ↗huggingface.co ↗Decision Index Vision 0.4
48Clef-omni Cloudflare47±2api $0.15/M input tokens +local~87GBdevelopers.cloudflare.com ↗System One Bench (Ali Alhashimi)Decision Index Vision 0.4Etsabary · decision benchmarks
49JPT-4B Qwen3.5-4B LoRA kirp47±5model files ↗huggingface.co ↗Decision Index Vision 0.4Benchmark Heaven (own decision evaluations)
50StartLux-Decision v1.1 2B StartLux46±11*model files ↗huggingface.co ↗JevalKit (Valen Team)
51Winnow-12B EldanRing46±5model files ↗huggingface.co ↗Decision Index Vision 0.4Benchmark Heaven (own decision evaluations)
52Aplomb 1 EmpirioLabs AI45±5request access ↗huggingface.co ↗Decision Index Vision 0.4
53RSI-Jev v6.1 VL 4B shgao44±5model files ↗huggingface.co ↗Decision Index Vision 0.4
54Valen-4B Valen44±5model files ↗huggingface.co ↗Decision Index Vision 0.4
55baselabs joey-1 (2B) baselabs44±6*api price unknownopenrouter.ai ↗Etsabary · decision benchmarks
56Jev-Omni akhilaaa344±5model files ↗huggingface.co ↗Decision Index Vision 0.4Benchmark Heaven (own decision evaluations)
57RSI-Jev v5.0 VL 3B shgao44±5model files ↗huggingface.co ↗Decision Index Vision 0.4
58InternLM Intern-Decision Qwen3.5-4B Shanghai AI Laboratory (InternLM)43±5model files ↗huggingface.co ↗Decision Index Vision 0.4JevalKit (Valen Team)
59QEV-2B ken-jo42±5model files ↗huggingface.co ↗Decision Index Vision 0.4
60Shisa DE-2 (repeat) Shisa.AI41±5model files ↗huggingface.co ↗Decision Index Vision 0.4
61TokenRhythm NeoHorse-Jev-4B TokenRhythm40±5model files ↗huggingface.co ↗Decision Index Vision 0.4Benchmark Heaven (own decision evaluations)
62vLLM-SR d3-nano (2B) vLLM Semantic Router39±5local~8.2GBhow to run › Decision Index Vision 0.4
63Jev-Style 2B v4 chaoliangUNSW37±5model files ↗huggingface.co ↗Decision Index Vision 0.4
64LiquidAI d1-omni-600M Liquid AI36±14*local~2.7GBhow to run › Benchmark Heaven (own decision evaluations)
65Valen-2B Valen35±5model files ↗huggingface.co ↗Decision Index Vision 0.4
66djev diffgemma (decision readout) Davipar35±5source code ↗github.com ↗Decision Index Vision 0.4
67razorback16 diffgemma (decision readout) vllm-project33±5source code ↗github.com ↗Decision Index Vision 0.4
68InternLM Intern-Decision Qwen3.5-2B Shanghai AI Laboratory (InternLM)32±5model files ↗huggingface.co ↗Decision Index Vision 0.4JevalKit (Valen Team)
69mmastrac diffgemma (decision readout) vllm-project31±5source code ↗github.com ↗Decision Index Vision 0.4
70QEV-0.8B ken-jo30±5model files ↗huggingface.co ↗Decision Index Vision 0.4
71StartLux-Decision v1.1 0.8B StartLux29±10*model files ↗huggingface.co ↗JevalKit (Valen Team)
72OneJev1.5-0.8B OmniJev28±5model files ↗huggingface.co ↗Decision Index Vision 0.4
73Winnow-E4B EldanRing25±5model files ↗huggingface.co ↗Decision Index Vision 0.4
74Valen-0.8B Valen24±5model files ↗huggingface.co ↗Decision Index Vision 0.4
75vLLM-SR d3-lite (0.8B) vLLM Semantic Router24±5local~4.5GBhow to run › Decision Index Vision 0.4
76Saina Helm 2 Omni (0.8B) Saina23±5model files ↗huggingface.co ↗Decision Index Vision 0.4
77JPT-0.8B Qwen3.5-0.8B LoRA kirp22±5model files ↗huggingface.co ↗Decision Index Vision 0.4Benchmark Heaven (own decision evaluations)
78InternLM Intern-Decision Qwen3.5-0.8B Shanghai AI Laboratory (InternLM)14±5model files ↗huggingface.co ↗Decision Index Vision 0.4JevalKit (Valen Team)
79vLLM-SR d3-edge (0.6B) vLLM Semantic Router10±5local~2.6GBhow to run › Decision Index Vision 0.4

79 of 79 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

79 models · 21 benchmarks · updated