Decision Index 0.3 Arts
We show this table for reference; we do not rank on it.
Decision Index 0.3 publishes chance-corrected arts scores for 112 evaluated systems.
Arts score on Decision Index 0.3 Arts — October 6, 2026
We mirror the published arts score view for Decision Index 0.3 Arts. The public snapshot contains 112 evaluated systems. Torchcast Decision 27B has the highest published score at 52.8 points, but the available coverage and evaluation setups do not establish a market leader. We do not use these results to rank models overall.
Torchcast Decision 27B
Not listed
Fastino GLiDE no-thinking (28B)
Not listed
Perplexity Decider v1.1 (27B)
Perplexity
112 evaluated systemsDecision ModelsCurrentDisplay onlyUpdated October 6, 2026
Arts score table (112 evaluated systems)
Showing 112 of 112| Rank | Model / configuration | Reported size | Weights | Score |
|---|---|---|---|---|
| 1 | Torchcast Decision 27BNot listedAnswered 100% · Latency 0.1s | 28B | Evaluated configuration | 52.8 points |
| 2 | Fastino GLiDE no-thinking (28B)Not listedCalibration 4 · Answered 100% · Latency 0.1s | 28B | Evaluated configuration | 51.7 points |
| 3 | Perplexity Decider v1.1 (27B)PerplexityModel sourceAnswered 100% · Latency 0.1s | 28B | Open | 51.4 points |
| 4 | Blink v0.3 26B-A4B (NVFP4)PixilabAIModel sourceAnswered 100% · Latency 0.0s | 26B | Open | 50.8 points |
| 5 | Surogate Rune 26B-A4B v3SurogateModel sourceCalibration 12 · Answered 99.6% · Latency 0.1s | 26B | Open | 50.4 points |
| 6 | GEV-26B-DecideautotrustModel sourceAnswered 100% · Latency 0.1s | 26B | Open | 47.7 points |
| 7 | Xor 1.2Not listedAnswered 100% · Latency 0.1s | 36B | Evaluated configuration | 47.2 points |
| 8 | Xor 26B-A4BjuspayModel sourceAnswered 100% · Latency 0.1s | 26B | Open | 46.9 points |
| 9 | Bespoke Nimble 9B v3bespokelabsModel sourceAnswered 100% · Latency 0.1s | 9.7B | Open | 46.3 points |
| 10 | JevNot listedCalibration 7.4 · Answered 100% · Latency 0.5s | Not disclosed | Evaluated configuration | 46.2 points |
| 11 | Cloudflare clefCloudflareModel sourceCalibration 4 · Answered 100% · Latency 0.1s | 28B | Open | 45.9 points |
| 12 | Eikos-27Bcaiovicentino1Model sourceCalibration 5.7 · Answered 100% · Latency 0.1s | 28B | Not listed | 45.5 points |
| 13 | JEV-27BautotrustModel sourceAnswered 100% · Latency 0.1s | 28B | Open | 45.4 points |
| 14 | reflex 27Bkshetrajna12Calibration 2.4 · Answered 100% · Latency 0.1s | 28B | Open | 44.8 points |
| 15 | vLLM-SR Decision 2.0 Vega 27BNot listedAnswered 100% · Latency 0.1s | 28B | Evaluated configuration | 44.6 points |
| 16 | Kev 27BjaredpalmerModel sourceCalibration 2.2 · Answered 100% · Latency 0.1s | 28B | Open | 44.4 points |
| 17 | Quyet-1.0-LargechinhncModel sourceAnswered 91.5% · Latency 0.1s | 33B | Open | 44.1 points |
| 18 | simple-jev · Qwen3.8-27B (featherless)Featherless AIModel sourceCalibration 11.3 · Answered 99.6% · Latency 0.4s | 28B | Evaluated configuration | 44.0 points |
| 19 | deck31b (Gemma 4 31B)Not listedAnswered 91.5% · Latency 0.2s | 33B | Evaluated configuration | 43.8 points |
| 20 | Decider chat · Gemma-4-31BMapikaModel sourceCalibration 4.7 · Answered 99.6% · Latency 0.1s | 33B | Evaluated configuration | 43.7 points |
| 21 | JADENot listedAnswered 100% · Latency 0.1s | 28B | Evaluated configuration | 43.4 points |
| 22 | Jebadiah 27Bfrontier-infraModel sourceCalibration 1.4 · Answered 100% · Latency 0.1s | 28B | Open | 43.0 points |
| 23 | AJev lora5 (Gemma 4 12B)andyzhang232Model sourceAnswered 100% · Latency 0.3s | 12B | Open | 42.3 points |
| 24 | Cloudflare clef-flashCloudflareModel sourceCalibration 2.5 · Answered 100% · Latency 0.1s | 9.7B | Open | 41.9 points |
| 25 | Decider chat · Qwen3.6-27BNot listedCalibration 2.1 · Answered 99.6% · Latency 0.1s | 28B | Evaluated configuration | 41.2 points |
| 26 | Decider 35B-A3BMapikaModel sourceCalibration 2.3 · Answered 100% · Latency 0.1s | 36B | Open | 40.7 points |
| 27 | JPT-35B-A3BkirpModel sourceAnswered 91.5% · Latency 0.3s | ~36B | Open | 40.0 points |
| 28 | decisio 0.4.0 (Qwen3.6-35B-A3B)Not listedAnswered 100% · Latency 0.1s | 36B | Evaluated configuration | 39.1 points |
| 29 | JoshuaSP diffusiongemma (open-jev)Not listedCalibration 21.6 · Answered 99.7% · Latency 0.3s | 26B | Evaluated configuration | 38.4 points |
| 30 | decisio 0.4.0 (Gemma 4 12B)Not listedAnswered 100% · Latency 0.0s | 12B | Evaluated configuration | 37.7 points |
| 31 | JevfireNot listedCalibration 5.2 · Answered 100% · Latency 0.1s | 28B | Evaluated configuration | 37.0 points |
| 32 | levinterfaze-aiModel sourceCalibration 6.4 · Answered 99.6% · Latency 0.1s | 4.7B | Open | 37.0 points |
| 33 | Lev1 3.7BNot listedAnswered 100% · Latency 0.0s | ~3.7B | Evaluated configuration | 36.9 points |
| 34 | djevMaisaCalibration 21.2 · Answered 98.9% · Latency 0.1s | 26B | Open | 36.5 points |
| 35 | Hopper 12B (trained)Not listedAnswered 91.5% · Latency 0.3s | 12B | Evaluated configuration | 36.4 points |
| 36 | vLLM-SR Decision 2.0 Lux 9BNot listedAnswered 100% · Latency 0.0s | 9.7B | Evaluated configuration | 36.3 points |
| 37 | ezjev 4B s2everettjfModel sourceAnswered 100% · Latency 0.0s | 4.7B | Open | 35.9 points |
| 38 | JevK5 9B v0.3.3alibiserikbayModel sourceAnswered 100% · Latency 0.0s | 9.7B | Open | 35.3 points |
| 39 | razorback16 openjev diffusiongemma (NVFP4, vLLM)Not listedCalibration 23.2 · Answered 99.6% · Latency 0.0s | 26B | Evaluated configuration | 35.1 points |
| 40 | Winnow-12BEldan RingModel sourceCalibration 16.8 · Answered 100% · Latency 0.1s | 12B | Open | 34.1 points |
| 41 | JEV-9BautotrustModel sourceAnswered 100% · Latency 0.1s | 9.7B | Open | 34.1 points |
| 42 | Ryotide Qwen v0.3.1Not listedAnswered 100% · Latency 0.1s | 4.0B | Evaluated configuration | 34.0 points |
| 43 | Kas 4BkpiyaModel sourceAnswered 91.5% · Latency 0.1s | 4.0B | Open | 33.8 points |
| 44 | JobeNot listedCalibration 12.3 · Answered 100% · Latency 0.1s | 4.7B | Evaluated configuration | 33.3 points |
| 45 | jiwo 4BeljiwoModel sourceAnswered 100% · Latency 0.1s | 4.7B | Open | 33.2 points |
| 46 | Decider 4BMapikaModel sourceCalibration 8.4 · Answered 99.6% · Latency 0.0s | 4.7B | Open | 33.2 points |
| 47 | mmastrac diffusiongemma (vLLM PR 57250)Not listedCalibration 20.2 · Answered 86.8% · Latency 0.1s | 26B | Evaluated configuration | 32.8 points |
| 48 | JevK5 v0.3Not listedAnswered 100% · Latency 0.0s | 4.7B | Evaluated configuration | 32.7 points |
| 49 | Hopper (G) 1.2HopitAIModel sourceCalibration 9.3 · Answered 99.6% · Latency 0.0s | 4.7B | Open | 32.6 points |
| 50 | Bespoke Nimble 9B v2bespokelabsModel sourceCalibration 2.4 · Answered 99.6% · Latency 0.1s | 9.7B | Open | 32.3 points |
| 51 | JPT-9BkirpModel sourceCalibration 7.7 · Answered 100% · Latency 0.1s | 9.7B | Open | 31.9 points |
| 52 | Intern-Decision-4BinternlmModel sourceCalibration 2.8 · Answered 99.6% · Latency 0.0s | 4.7B | Open | 31.6 points |
| 53 | SemIfNot listedCalibration 9.9 · Answered 86.1% · Latency 0.1s | 4.7B | Evaluated configuration | 31.5 points |
| 54 | Jet v6.2michaljachModel sourceCalibration 14.1 · Answered 99.8% · Latency 0.0s | 4.7B | Open | 31.1 points |
| 55 | Jev-Omniakhilaaa3Model sourceCalibration 16.1 · Answered 99.6% · Latency 0.1s | 12B | Open | 30.6 points |
| 56 | vLLM-SR Decision 2.0 Nox 4BNot listedAnswered 100% · Latency 0.0s | 4.2B | Evaluated configuration | 30.3 points |
| 57 | openvonsNot listedCalibration 37.1 · Answered 100% · Latency 0.0s | 4.0B | Evaluated configuration | 30.3 points |
| 58 | mini-jevNot listedCalibration 34.6 · Answered 86.8% · Latency 0.1s | 4.0B | Evaluated configuration | 30.0 points |
| 59 | JPT-4BkirpModel sourceCalibration 7.9 · Answered 100% · Latency 0.1s | 4.7B | Open | 29.3 points |
| 60 | Solomon v1.1Not listedCalibration 8.1 · Answered 75% · Latency 0.2s | 28B | Evaluated configuration | 28.9 points |
| 61 | Winnow-E4BEldanRingModel sourceCalibration 5.8 · Answered 99.6% · Latency 0.0s | 8.0B | Open | 27.9 points |
| 62 | Sieve 9Bsthanika-aiModel sourceAnswered 100% · Latency 0.1s | 9.7B | Open | 27.5 points |
| 63 | Gevva E4BdavidburhansModel sourceAnswered 100% · Latency 0.1s | 8.0B | Open | 26.7 points |
| 64 | Tev1-4B-experimentaltogethercomputerModel sourceCalibration 10.4 · Answered 86.2% · Latency 0.0s | 4.7B | Open | 26.2 points |
| 65 | Intelif Qwen3-4BNot listedAnswered 100% · Latency 0.0s | 4.0B | Evaluated configuration | 25.5 points |
| 66 | Decider 2BMapikaModel sourceCalibration 7.7 · Answered 100% · Latency 0.0s | 2.3B | Open | 22.5 points |
| 67 | Sieve 2Bsthanika-aiModel sourceAnswered 100% · Latency 0.1s | 2.3B | Open | 22.4 points |
| 68 | Metask-Jev-4BWayfind (metask-ai)Model sourceCalibration 10.3 · Answered 86.8% · Latency 0.1s | 4.7B | Open | 22.1 points |
| 69 | Jev-Style 2B v3Not listedAnswered 100% · Latency 0.1s | 2.3B | Evaluated configuration | 22.0 points |
| 70 | Kev 4B r10jaredpalmerModel sourceCalibration 3.2 · Answered 100% · Latency 0.1s | 4.7B | Open | 21.5 points |
| 71 | Bekko System One v0 400MhotchpotchModel sourceAnswered 100% · Latency 0.0s | ~400M | Open | 21.5 points |
| 72 | RSI-Jev v5.0 VL 3BshgaoModel sourceAnswered 100% · Latency 0.0s | 4.7B | Open | 21.4 points |
| 73 | Kev 9B v2Not listedCalibration 4.5 · Answered 100% · Latency 0.1s | 9.7B | Evaluated configuration | 20.2 points |
| 74 | Intern-Decision-2BinternlmModel sourceCalibration 6.1 · Answered 99.6% · Latency 0.0s | 2.3B | Open | 19.4 points |
| 75 | open-jev (pngwn)Not listedCalibration 5.9 · Answered 99.8% · Latency 0.1s | 4.7B | Evaluated configuration | 18.6 points |
| 76 | this-that 1.2Not listedCalibration 19.8 · Answered 99.6% · Latency 0.0s | 1.9B | Evaluated configuration | 17.7 points |
| 77 | Kodiak v0.2 1B (accuracy)cortex-agent-llcModel sourceAnswered 99.9% · Latency 0.1s | 3.0B | Open | 16.9 points |
| 78 | Jevstral 8BAmirBrahamModel sourceAnswered 100% · Latency 0.0s | ~8.0B | Open | 16.6 points |
| 79 | vLLM-SR Decision 2.0 Sol 2BNot listedAnswered 100% · Latency 0.0s | 2.3B | Evaluated configuration | 15.8 points |
| 80 | Bekko System One v0 68MhotchpotchModel sourceAnswered 100% · Latency 0.0s | ~68M | Open | 15.8 points |
| 81 | EXAONE-4.0-1.2B-JEV v0.3Not listedAnswered 100% · Latency 0.1s | ~1.3B | Evaluated configuration | 15.5 points |
| 82 | NeoHorse-Jev-4BTokenRhythmModel sourceCalibration 10.4 · Answered 99.6% · Latency 0.0s | 4.7B | Open | 14.2 points |
| 83 | Gevva E2BdavidburhansModel sourceAnswered 100% · Latency 0.0s | 5.1B | Open | 14.0 points |
| 84 | jiwo 0.8BeljiwoModel sourceAnswered 100% · Latency 0.0s | 870M | Open | 13.5 points |
| 85 | Qwen-2.5-1B-RLCDharshathegModel sourceCalibration 20.5 · Answered 99.7% · Latency 0.0s | 1.5B | Open | 11.8 points |
| 86 | OneJev 0.8BOmniJevModel sourceAnswered 100% · Latency 0.1s | 870M | Open | 10.3 points |
| 87 | LFM2.5-2.6B-RLCDmonotykamaryModel sourceCalibration 25.4 · Answered 99.5% · Latency 0.0s | 2.7B | Open | 10.0 points |
| 88 | vLLM-SR Decision 2.0 Eos 0.8BNot listedAnswered 100% · Latency 0.0s | 870M | Evaluated configuration | 9.4 points |
| 89 | Bosun v3.1 1.7BHanno-LabsModel sourceCalibration 13 · Answered 99.6% · Latency 0.0s | 1.7B | Open | 8.6 points |
| 90 | JPT-0.8BkirpModel sourceCalibration 6.9 · Answered 100% · Latency 0.1s | 873M | Open | 8.0 points |
| 91 | vLLM-SR Decision 2.0 Kai 0.6BNot listedAnswered 100% · Latency 0.0s | 600M | Evaluated configuration | 8.0 points |
| 92 | Jev-Style 0.8B v3Not listedAnswered 99.9% · Latency 0.0s | 870M | Evaluated configuration | 8.0 points |
| 93 | Intern-Decision-0.8BinternlmModel sourceCalibration 2.5 · Answered 99.6% · Latency 0.0s | 873M | Open | 8.0 points |
| 94 | Sifr 0.8B v3.1Not listedAnswered 100% · Latency 0.0s | 870M | Evaluated configuration | 7.8 points |
| 95 | Dinah-0LukitaduarteModel sourceAnswered 100% · Latency 0.0s | 150M | Open | 7.0 points |
| 96 | Bosun v3.1 0.6BClause LogicModel sourceCalibration 14.2 · Answered 99.6% · Latency 0.0s | 596M | Open | 6.6 points |
| 97 | system-one-gemmaNot listedCalibration 23.9 · Answered 99.9% · Latency 0.0s | 268M | Evaluated configuration | 6.6 points |
| 98 | Von 1.3Not listedAnswered 100% · Latency 0.0s | 400M | Evaluated configuration | 6.5 points |
| 99 | GLiNER2.5-DecidefastinoModel sourceCalibration 8.8 · Answered 99.6% · Latency 0.0s | 486M | Open | 6.4 points |
| 100 | LayaConvai InnovationsModel sourceCalibration 14 · Answered 99.6% · Latency 0.0s | 421M | Open | 6.0 points |
| 101 | Tev1-0.8B-experimentaltogethercomputerModel sourceCalibration 12.6 · Answered 86.2% · Latency 0.0s | 873M | Open | 5.7 points |
| 102 | DM-JEPA 1.1Not listedAnswered 91.5% · Latency 0.1s | 149M | Evaluated configuration | 5.1 points |
| 103 | JevK5 LitealibiserikbayModel sourceAnswered 69% · Latency 0.0s | 300M | Open | 4.9 points |
| 104 | Bekko System One v0 17MhotchpotchModel sourceAnswered 100% · Latency 0.0s | ~17M | Open | 4.9 points |
| 105 | LavoirmoganaiModel sourceCalibration 14.9 · Answered 99.7% · Latency 0.0s | 396M | Open | 4.5 points |
| 106 | Kev 0.8B r15Not listedCalibration 4 · Answered 100% · Latency 0.0s | 870M | Evaluated configuration | 4.4 points |
| 107 | LFM2.5-350M-RLCDnotnotsamuelModel sourceCalibration 56.8 · Answered 100% · Latency 0.0s | 354M | Open | 4.1 points |
| 108 | CLM-v0.1-8BContrastive-LMModel sourceCalibration 32.3 · Answered 99.6% · Latency 0.0s | 8.2B | Open | 2.5 points |
| 109 | ZevNot listedAnswered 100% · Latency 0.0s | Not disclosed | Evaluated configuration | 2.5 points |
| 110 | Julia 1SupersonicLabsModel sourceCalibration 42 · Answered 99.6% · Latency 0.0s | ~141M | Open | 2.3 points |
| 111 | jeffLogan MarkewichCalibration 9.7 · Answered 100% · Latency 0.0s | ~576M | Open | 0.9 points |
| 112 | VerdictNot listedCalibration 15.4 · Answered 40.2% · Latency 0.0s | 151M | Evaluated configuration | 0.0 points |
How to read this leaderboard
The source uses a 0 to 100 scale, with 0 at chance and 100 at perfect performance. Scores are coverage-adjusted; an unanswered or unsupported request counts as wrong.
Operator receipt: 112 sourced rows are currently displayable on this page; the highest published score among these 112 evaluated systems is Torchcast Decision 27B at 52.8 points, which does not establish a market leader.
Honest limit: This is an area score from a composite that includes private tasks. It is display-only and does not enter general model rankings.
How we show Decision Index 0.3
The Decision Index 0.3 board lists 112 evaluated systems. This snapshot follows source commit f03e5a6 and keeps the arts score values and size labels published on the board.
The full score weights 37 public benchmarks at 20%, private tests of the same skills at 50%, and private tasks from new domains at 30%. The source reports 110,201 decisions. Scores are chance-corrected and coverage-adjusted; unsupported or unanswered requests count as wrong.
The published aggregates include private task results, but the task contents and item-level answers are not public. We show the board as external reference data, separate from general model rankings.
Snapshot
The published Decision Index 0.3 Arts snapshot places Torchcast Decision 27B first at 52.8 points. The third row is 1.4 points behind. The broader top-10 range is 6.6 points, so many of the published results sit in a relatively narrow band.
112 evaluated systems are shown for Decision Index 0.3 Arts. The benchmark falls in the Decision Models category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. Decision Index 0.3 Arts is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About Decision Index 0.3 Arts
Year
2026
Tasks
Arts area of the Decision Index 0.3 evaluation
Format
Chance-corrected area score
Difficulty
Arts and human-taste decision tasks
The area score appears on the board beside the full score. The full score combines public benchmarks at 20%, private tests of the same skills at 50%, and private tasks from new domains at 30%. Private task contents and item-level results are not published.
Freshness and provenance
Version
Decision Index 0.3
Refresh cadence
Pinned benchmark-owner snapshot
Staleness state
Current
Question availability
37 public benchmarks; same-skill and new-domain task contents and item-level results are private
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does Decision Index 0.3 Arts measure?
Decision Index 0.3 publishes chance-corrected arts scores for 112 evaluated systems.
Which model leads the published Decision Index 0.3 Arts snapshot?
Torchcast Decision 27B currently leads the published Decision Index 0.3 Arts snapshot with 52.8 points arts score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
How many models are evaluated on Decision Index 0.3 Arts?
The October 6, 2026 snapshot contains 112 AI models.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 5,500+ readers.
One email each week. Unsubscribe anytime.