vera-large

+ contribute

vera-large is an open-weights decision model from scar-ai. Its published size is 25.63B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine vera-large; reported model vera-large. Type: full fine-tune; 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

· Weights licence ↗ · Parameter count ↗

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

69.5±1.5#20 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of vera-large, out of 357 with a score, then more from scar-ai.

#	model	score	where	released
18	AutoTrust-JEV-27B v1.1 AutoTrust AI Lab	70±1	model files	2026-10-17
19	MISA AI 2.0 Decision Plus · oak 1.1 (31B) MISA JSC	70±2	model files
20	vera-large scar-ai	70±2	model files
21	d1-ultra Liquid AI	69±2	api price unknown	2026-10-15
22	KnowLine 26B-A4B Gen2.5 PelaAI	69±2	model files	2026-10-22
	more from scar-ai
239	vera-core-2 scar-ai	46±1	model files
303	vera-spark scar-ai	31±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #43 of 250 · 5.4% of its score · 6 tests

Beats Fastino GLiDE 1.2, vLLM-SR d3-ultra (Decision 3.0, 27B), AutoTrust-JEV-27B v1.1 here, though they rank higher overall. Trails baselabs joey-1 (2B), Solomon v1.1, Clef-flash 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	85.0% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 157/236	easy · avg 70%	▇ 1.6%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	68.5% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 212/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	80.7% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 191/243	medium · avg 37%	▇ 0.9%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	89.6% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 210/246	easy · avg 72%	▇ 0.9%	noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.5% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 203/246	very easy · avg 92%	▇ 0.8%	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▁▁▁·▁▁▁▁▃▃█▅ #14 of 258 · 8.1% 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 StartLux-Decision v1.1 4B, VisionJEV 1.0.0 (27B), OneShot 27B 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	49.3% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 222/246	medium · avg 38%	▇ 3.4%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	62.0% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 232/246	medium · avg 47%	▇ 2.9%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	89.5% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 239/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	74.2% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 147/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	93.4% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 229/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	96.8% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 230/238	easy · avg 83%	▇ 0.3%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	63.2% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #12 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, vLLM-SR d3 (27B) 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	80.2% ✎	▁▂▃▅▅█▃····▁ beats 236/246	medium · avg 60%	▇▇ 5.5%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	88.3% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 246/246	easy · avg 74%	▇▇ 5.1%	typical
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	68.5% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 224/246	medium · avg 44%	▇ 2.9%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	97.7% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 234/246	very easy · avg 85%	▇ 2.5%	sharp · maxed out
Decision Index 0.4.1: ACOS (per-review F1) submitted	63.5% ✎	▁··▂▃▃▅▇█▇▃▃ beats 239/246	hard · avg 22%	▇ 2.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	79.7% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 217/246	medium · avg 62%	▇ 1.1%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	86.1% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 240/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	85.9% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 239/246	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	94.5% ✎	▁···▁▁▁▁▃▆█▃ beats 227/246	easy · avg 84%	▇ 0.5%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▃ #1 of 247 · 10% of its score · 6 tests

Beats Jeffan-31b-1710, baselabs mammoth-1 (27B), Sieve 31B v3 here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: New Yorker (accuracy) submitted	80.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 221/246	medium · avg 61%	▇▇ 4.0%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	68.7% ✎	▁·▁▃▂▂▅█▄▃▁▁ beats 235/246	medium · avg 60%	▇ 2.5%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	66.4% ✎	▁········▁▇█ beats 215/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	60.1% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 176/237	hard · avg 21%	▇ 1.4%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	99.5% ✎	▁█▄▄▅█▆▅▄▁▁▃ beats 246/246	easy · avg 83%	▇ 0.8%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	61.9% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 219/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #44 of 263 · 42% of its score · 14 tests

Trails Solar Decide, Clef-omni, GPT-6 Luna Decisions 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	70.7% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 213/246	medium · avg 46%	▇▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	83.4% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 208/246	easy · avg 66%	▇▇ 5.7%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	87.0% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 208/246	easy · avg 70%	▇▇ 5.5%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	50.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 195/246	medium · avg 39%	▇▇ 4.4%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	82.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 224/246	medium · avg 45%	▇ 3.7%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	95.3% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 236/246	easy · avg 78%	▇ 2.6%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	27.6% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 122/246	hard · avg 22%	▇ 2.4%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	66.5% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 193/246	medium · avg 60%	▇ 1.5%	blunt · at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	96.8% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 181/246	very easy · avg 90%	▇ 1.5%	sharp · maxed out
Decision Index 0.4.1: CRUXEval (accuracy) submitted	84.4% ✎	██▄▃▃▄▁▁···▁ beats 210/246	medium · avg 58%	▇ 1.2%	noisy
Decision Index 0.4.1: ChessBench (accuracy) submitted	17.8% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 146/246	hard · avg 16%	▇ 1.1%	blunt
Decision Index 0.4.1: CLadder (accuracy) submitted	78.1% ✎	▁███▆▅▃▃▁▁▁▁ beats 168/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.3% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 228/246	very easy · avg 96%	▇ 0.6%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	12.2% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 114/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 11% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	61.2100 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 212/247	avg 41.206 points	▇▇▇ 7.4%	blunt
Decision Index 0.4.1: private new domains (equated points)	71.3300 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 216/247	avg 38.861 points	▇▇ 4.1%	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/scar-ai ↗

$ how the score was worked out · Decision Index 0.4.1 99%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 99%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 69.5

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]	63.2%	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