vera-spark

+ contribute

vera-spark is an open-weights decision model from scar-ai. Its published size is 0.64B parameters. Licence: apache-2.0.

Catalogue identity notes

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

31.2±1.0#301 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

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

#	model	score	where	RAM
301	Crivo-150M v2 tardellirs	32±1	model files
302	Bekko System One v0 400M hotchpotch	32±1	model files
303	vera-spark scar-ai	31±1	model files
304	vLLM-SR Decision 2.0 Eos 0.8B vLLM Semantic Router	31±1	local	~5.8GB
305	DecisionTune 1.0 DecisionTune	31±1	model files
	more from scar-ai
20	vera-large scar-ai	70±2	model files
239	vera-core-2 scar-ai	46±1	model files

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

$ what it's good at

tools & automation▁▃▃▁▁▂▃▄▆██▆ #227 of 250 · 10% of its score · 6 tests

Beats DM-JEPA 1.1, JEV FLAN-T5 Large public v2 (342M), Bekko System One v0 400M here, though they rank higher overall. Trails Prumo (rule-based engine), Crivo-17M, JevK5 Lite here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	49.2% ✎	▁▂▃▁▁▂▂▄▅▆█▁ beats 23/246	very easy · avg 92%	▇▇ 5.7%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	22.6% ✎	▁▁▁▁▁▁▃▂▃▂█▂ beats 19/236	easy · avg 70%	▇ 2.1%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	28.4% ✎	▁▁▃▂▃▅▅▆█▇█▃ beats 13/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	39.3% ✎	▁▁▁▁▁·▃▁▁▄█▁ beats 18/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 18/243	medium · avg 37%	▇ 0.2%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	58.0% ✎	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▁▁▁·▁▁▃▁▃▃█▅ #230 of 258 · 4.6% of its score · 7 tests

Beats Sieve 2B, Strands Decider 2B (Hobson v21), Valen-0.8B here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA, Crivo-32M v2, Jev-Style 0.8B v3 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	27.5% ✎	▁▁▁▁▁▁▃▂▃▃█▅ beats 27/246	medium · avg 47%	▇ 1.3%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	25.4% ✎	▁▁▁▁▁▁▃▂▂▄▇█ beats 32/246	medium · avg 38%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	40.7% ✎	▁▁▁▁▁▁▃▂▃▆█▄ beats 21/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	70.3% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 101/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	42.8% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 0/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	68.5% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 36/238	easy · avg 79%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	49.4% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #178 of 256 · 24% of its score · 9 tests

Beats Nari Decision 4B v3.2, InternLM Intern-Decision Qwen3.5-4B, Solar Decide Flash here, though they rank higher overall. Trails DecisionTune 1.0 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: HellaSwag (accuracy) submitted	78.5% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 77/246	very easy · avg 85%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	59.2% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 41/246	easy · avg 74%	▇▇ 5.3%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	41.9% ✎	▁▂▃▅▅█▂····▁ beats 43/246	medium · avg 60%	▇▇ 3.8%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	38.4% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 85/246	medium · avg 44%	▇ 1.2%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	55.9% ✎	▁▁▁▁▁▁▁▃▂▇▇█ beats 42/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	56.3% ✎	▁···▁▁▁▃▃▆█▃ beats 17/246	easy · avg 84%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	42.7% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 44/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	38.1% ✎	▁▁▁▁▁▁▁▁▃▃▆█ beats 37/246	easy · avg 66%	▇ 0.6%	at its level · noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ACOS (per-review F1) submitted	7.9% ✎	▁··▂▃▃▅▇█▇▃▃ beats 42/246	hard · avg 22%	▇ 0.3%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #187 of 247 · 7.2% of its score · 6 tests

Beats Kev 9B v2, vLLM-SR d3-nano (2B), Kev 4B r10 here, though they rank higher overall. Trails Qwen-2.5-1B-RLCD (decision readout), Bekko System One v0 68M, Crivo-17M 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	35.4% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 26/246	medium · avg 61%	▇ 2.9%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	66.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 60/246	easy · avg 83%	▇ 1.7%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	54.3% ✎	▁·▁▃▃▂▅█▄▂▁▁ beats 51/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	50.9% ✎	▁········▁▇█ beats 26/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	40.9% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 81/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	1.7% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 38/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▂▂▃▂▃▃▅▅▆█▂ #222 of 263 · 49% of its score · 14 tests

Beats Decision-1.0-Eos-0.8B (DecisionBench 3c2d6326), Amber 0.4B, Crivo-400M here, though they rank higher overall. Trails laya (DecisionBench 1c5edc17), LFM2.5-2.6B-RLCD, InternLM Intern-Decision Qwen3.5-0.8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	72.5% ✎	▁▁▂▃▂▂▂▂▃▆█▅ beats 32/246	very easy · avg 96%	▇▇▇▇▇ 11%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	59.6% ✎	▂▂▂▃▂▂▁▃▄▆█▆ beats 41/246	very easy · avg 90%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	42.5% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 42/246	easy · avg 70%	▇▇▇ 6.5%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	37.8% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 26/246	easy · avg 66%	▇▇ 5.2%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	22.7% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 43/246	medium · avg 46%	▇▇ 4.9%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	71.7% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 95/246	easy · avg 78%	▇ 3.5%	at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	27.6% ✎	▂▆▅▅▆█▆▃▁··▁ beats 41/246	medium · avg 39%	▇ 1.8%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	18.9% ✎	▁··▄█▆▆▆▅▅▃▁ beats 26/246	medium · avg 45%	▇ 1.5%	sharp

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	52.1% ✎	▁▁▃█▅▄▁▁▁▁▁▁ beats 44/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	53.2% ✎	▁███▆▅▃▃▁▁▁▁ beats 30/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	40.2% ✎	██▄▃▃▄▁▁···▁ beats 56/246	medium · avg 58%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	1.5% ✎	▁▁▃▁▁▁▁▂▅█▂▁ beats 20/246	hard · avg 22%	▇ 0.5%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	7.4% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 8/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	15.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 211/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 5.7% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	14.2500 points ✎	▂▂▃▃▃▃▄▅▅▇█▃ beats 24/247	avg 41.206 points	▇ 3.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	6.1200 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 1/247	avg 38.861 points	▇ 2.0%	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 0.4.1 100%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 31.2

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	58.0%	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]	49.4%	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