whatmodel.sh / decision / Torchcast Decision 27B

Torchcast Decision 27B

+ contribute

Torchcast Decision 27B is an open-weights decision model from Torchcast AI, released 1 October 2026. Its published size is 27.8B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine torchcast-decision-27b; reported model Torchcast Decision 27B. Type: LoRA; technique: autoregressive. Comparison entry; no current run command, API price or speed inferred from the benchmark. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run.

Model information sources

Release date ↗ · Weights licence ↗ · Parameter count ↗

Publisher parameter count; includes the served backbone, not just adapter size.

66.5±1.4#41 of 355 decision modelsfrom 44 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of Torchcast Decision 27B, out of 357 with a score.

#	model	score	where	released
39	Aleria Judge 1.1.1 (Gemma 4 31B) (decision readout) ALERIA-ML	67±1	source code	2026-10-19
40	Cerno 27B apertixai	67±1	model files
41	Torchcast Decision 27B Torchcast AI	67±1	model files	2026-10-01
42	bosun-v3.1-1.7b (DecisionBench 2ef2d972) Hanno Labs	67±2	model files
43	Decider 31B (NVFP4) Mapika	66±1	model files	2026-10

see all decision models · find the ones that fit your machine

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #36 of 250 · 5.6% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, Ainvest-Decision-27B v1.0 here, though they rank higher overall. Trails Solomon v1.1, Clef-flash, Clef-omni here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: API-Bank (accuracy) submitted	85.2% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 165/236	easy · avg 70%	▇ 1.7%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	68.4% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 208/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	89.8% ✎	█▁▁▃▄▄▆▄▃▂▁▃ beats 205/243	medium · avg 37%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	89.0% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 203/246	easy · avg 72%	▇ 0.9%	noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.7% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 211/246	very easy · avg 92%	▇ 0.9%	sharp · maxed out · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.8% ✎	no other model yet		—	failed run: Publisher excludes this protocol because its prompt reveals GPT-4 as the best route. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

retrieval & classification▁▁▁·▁▁▁▁▃▃█▅ #20 of 258 · 7.5% of its score · 7 tests

Beats Fastino GLiDE 1.2, KnowLine 31B Gen1, Ainvest-Decision-27B v1.0 here, though they rank higher overall. Trails JEV-35B, StartLux-Decision v1.1 4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	50.7% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 242/246	medium · avg 38%	▇ 3.1%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	61.6% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 228/246	medium · avg 47%	▇ 2.7%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	89.4% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 237/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	70.3% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 130/245	easy · avg 70%	▇ 0.5%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	91.1% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 200/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	93.5% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 184/238	easy · avg 83%	▇ 0.3%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	73.4% ✎	no other model yet		—	failed run: Publisher reports a builder bug exposing dialogue turns after the classified turn; awaiting corrected rerun. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

language understanding▂▂▂▃▂▅▆▃█▆▄▃ #13 of 256 · 21% of its score · 9 tests

Beats Sieve 31B v3, KnowLine 31B Gen1, Ainvest-Decision-27B v1.0 here, though they rank higher overall. Trails Clef-omni here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ANLI (macro-F1) submitted	78.8% ✎	▁▂▃▅▅█▃····▁ beats 227/246	medium · avg 60%	▇▇ 5.3%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	86.2% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 227/246	easy · avg 74%	▇▇ 5.0%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	97.6% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 231/246	very easy · avg 85%	▇ 2.8%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	50.1% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 132/246	medium · avg 44%	▇ 2.7%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	57.3% ✎	▁··▂▃▃▅▇█▇▃▃ beats 230/246	hard · avg 22%	▇ 1.8%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	82.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 241/246	medium · avg 62%	▇ 1.1%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	86.5% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 242/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	86.0% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 241/246	easy · avg 66%	▇ 0.7%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	93.2% ✎	▁···▁▁▁▁▃▆█▃ beats 194/246	easy · avg 84%	▇ 0.5%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #45 of 247 · 10% of its score · 6 tests

Beats Jeffan-31b-1710, vLLM-SR d3-turbo v1.1 (27B), Nace.AI Drex Max v1 (27B) here, though they rank higher overall. Trails Kas 4B, baselabs joey-1 (2B), Clef-flash here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: New Yorker (accuracy) submitted	79.0% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 209/246	medium · avg 61%	▇▇ 3.9%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.6% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 163/246	medium · avg 60%	▇ 2.3%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	50.7% ✎	▄▅▅▃▆▅▃▅▃▅▃█ beats 166/237	hard · avg 21%	▇ 1.3%	sharp · at its level · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	70.2% ✎	▁········▁▇█ beats 242/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	95.4% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 201/246	easy · avg 83%	▇ 0.8%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	60.3% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 205/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #53 of 263 · 41% of its score · 14 tests

Beats OneJev1.6-27B, baselabs elephant-1 (9B), StartLux-Decision v1.1 9B here, though they rank higher overall. Trails Solar Decide, Clef-flash, Clef-omni here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	70.4% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 209/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	80.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 196/246	easy · avg 66%	▇▇ 5.7%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	86.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 202/246	easy · avg 70%	▇▇ 5.6%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	51.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 207/246	medium · avg 39%	▇▇ 4.0%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	64.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 172/246	medium · avg 45%	▇ 3.6%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	93.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 223/246	easy · avg 78%	▇ 2.6%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	15.0% ✎	▁▁▁▁▁▁▁▃▅█▂▁ beats 56/246	hard · avg 22%	▇ 2.1%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.1% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 199/246	very easy · avg 90%	▇ 1.7%	sharp · maxed out

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	67.3% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 200/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	78.6% ✎	██▄▃▃▄▁▁···▁ beats 191/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ChessBench (accuracy) submitted	18.1% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 153/246	hard · avg 16%	▇ 1.0%	blunt
Decision Index 0.4.1: CLadder (accuracy) submitted	74.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 152/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.3% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 232/246	very easy · avg 96%	▇ 0.7%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	13.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 155/246	very hard · avg 13%	▇ 0.0%	blunt

other tests4 not in a task · 14% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	57.7500 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 192/247	avg 41.206 points	▇▇▇ 6.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	67.1000 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 207/247	avg 38.861 points	▇ 3.6%	blunt
Benchmark Heaven jevbench v1.6.1: intelligence (points)	71.7519 points ✎	▃···▃·▃▃█▅▅█ beats 11/13	avg 32.166 points	▇ 2.9%	blunt
Benchmark Heaven jevbench v1.6.1: calibration (points)	91.3794 points ✎	▂······▂▆▂██ beats 12/13	avg 70.133 points	▇ 0.8%	blunt

$ where to run it

Download model files ↗
Published model files verified. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. A local run command and hardware requirements have not been verified for this entry. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/torchcast-ai ↗

$ how the score was worked out · Decision Index 0.4.1 95%, Benchmark Heaven (own decisio… 4%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Decision Index 0.4.1 · submitted; independent execution unverified	42	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%	CC BY 4.0
Benchmark Heaven (own decision evaluations)	2	▇ 4%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 66.5

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.8%	failed run: Publisher excludes this protocol because its prompt reveals GPT-4 as the best route. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json
Decision Index 0.4.1	Decision Index 0.4.1: SGD/SGD-X (macro-F1) [correct]	73.4%	failed run: Publisher reports a builder bug exposing dialogue turns after the classified turn; awaiting corrected rerun. Evidence: https://huggingface.co/spaces/multimodalart/jev-decision-index/blob/c130faf65f82e81d3bdefb01e758c712dc5c5199/data/index.json

$ improve this page

Update model information Add a place to run it Add a test result Propose a benchmark Correct a benchmark score Edit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated 2026-11-03 02:37 UTC · sources and licences · json