Crivo-32M v2

+ contribute

Crivo-32M v2 is an open-weights decision model from tardellirs. Its published size is 0.03B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine crivo-32m-v2; reported model Crivo-32M v2. 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.

26.8±1.0#322 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Crivo-32M v2, out of 357 with a score, then more from tardellirs.

#	model	score	where
322	mxbai-rerank-base-v2 (DecisionBench 3ea9d4df) mixedbread-ai	27±2	model files
323	open-jev-deberta-v3-large (DecisionBench 19bf9a64) com-kotobalabs	27±2	model files
324	Crivo-32M v2 tardellirs	27±1	model files
325	LFM2.5-2.6B-RLCD monotykamary	26±1	model files
326	gliner2-large-v1 (DecisionBench f32ea6ef) Fastino	26±2	model files
	more from tardellirs
253	Crivo-1B tardellirs	43±1	model files
279	Crivo-400M tardellirs	37±1	model files
301	Crivo-150M v2 tardellirs	32±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▃▃▄▆██▆ #208 of 250 · 10% of its score · 6 tests

Beats Cam1, InternLM Intern-Decision Qwen3.5-2B, JEV Ettin 150M here, though they rank higher overall. Trails 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	77.0% ✎	▁▂▁▁▁▃▂▄▅▆█▁ beats 41/246	very easy · avg 92%	▇▇▇ 6.4%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	57.1% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 65/236	easy · avg 70%	▇ 1.8%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	62.4% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 74/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	53.1% ✎	▁▁▁▁▁·▁▁▃▄█▁ beats 38/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	23.9% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 94/243	medium · avg 37%	▇ 0.1%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	54.2% ✎	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▁▁▁·▁▁▁▃▃▃█▅ #209 of 258 · 4.5% of its score · 7 tests

Beats Metask-Jev-4B, Jobe Qwen3.5-4B (decision readout), openvons Qwen3-4B (decision readout) here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA 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	36.0% ✎	▁▁▁▁▁▁▂▃▃▃█▅ beats 49/246	medium · avg 47%	▇ 1.3%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	26.0% ✎	▁▁▁▁▁▁▃▂▂▄▇█ beats 34/246	medium · avg 38%	▇ 1.2%	blunt
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	84.8% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 77/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	78.4% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 136/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	46.4% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 3/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	86.1% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 146/238	easy · avg 79%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	47.4% ✎	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▃▂▂▃▂▅▆▃█▆▄▃ #245 of 256 · 23% of its score · 9 tests

Trails CLM-v0.1-8B Qwen3-8B heads, jeff GLiFormer-large (decision readout), Verdict 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	33.0% ✎	▃▄▂▂▄▇▃▇█▅▃▁ beats 10/246	very easy · avg 85%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	51.3% ✎	▁▁▁▂▃▃▃▄▇▇█▄ beats 21/246	easy · avg 74%	▇▇ 5.3%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	34.6% ✎	▁▂▃▅▅█▂····▁ beats 23/246	medium · avg 60%	▇ 3.6%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	6.4% ✎	▁·▁·▃▁▂▄▅█▇▄ beats 4/246	medium · avg 44%	▇ 1.1%	typical
Decision Index 0.4.1: FinEntity (macro-F1) submitted	76.0% ✎	▁···▁▁▁▁▃▆█▃ beats 59/246	easy · avg 84%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	71.2% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 81/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	64.9% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 120/246	medium · avg 62%	▇ 0.7%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	66.1% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 82/246	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	17.3% ✎	▁··▂▃▃▅▇█▇▃▃ beats 90/246	hard · avg 22%	▇ 0.3%	too hard for it · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #141 of 247 · 7.0% of its score · 6 tests

Beats OneJev1.6-4B, Nace.AI Drex v1.5, Jegue 0.1 (9B) 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	46.2% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 53/246	medium · avg 61%	▇ 2.8%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	84.8% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 106/246	easy · avg 83%	▇ 1.8%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	49.2% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 13/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	52.0% ✎	▁········▁▇█ beats 34/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	37.1% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 30/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	0.1% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 5/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▃▂▂▂▃▃▅▅▆█▂ #254 of 263 · 49% of its score · 14 tests

Trails CLM-v0.1-8B Qwen3-8B heads, jeff GLiFormer-large (decision readout), Verdict 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	48.2% ✎	▁▃▂▁▂▂▂▂▃▆█▅ beats 9/246	very easy · avg 96%	▇▇▇▇▇ 14%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	29.4% ✎	▃▂▂▂▂▂▁▃▄▆█▆ beats 8/246	very easy · avg 90%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	29.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 7/246	easy · avg 70%	▇▇ 6.2%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	36.4% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 19/246	easy · avg 66%	▇▇ 4.9%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	12.1% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 5/246	medium · avg 46%	▇▇ 4.1%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	50.5% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 9/246	easy · avg 78%	▇ 3.6%	at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	27.6% ✎	▂▆▅▅▆█▆▃▁··▁ beats 40/246	medium · avg 39%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	17.8% ✎	▁··▄█▆▆▆▅▅▃▁ beats 10/246	medium · avg 45%	▇ 1.3%	sharp

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	39.5% ✎	▃▁▂█▅▄▁▁▁▁▁▁ beats 11/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	51.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 23/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	42.6% ✎	██▄▃▃▄▁▁···▁ beats 71/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	0.1% ✎	▃▁▁▁▁▁▁▂▅█▂▁ beats 7/246	hard · avg 22%	▇ 0.4%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.6% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 36/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	15.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 208/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 5.6% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	17.6000 points ✎	▂▂▃▃▃▃▄▅▅▇█▃ beats 31/247	avg 41.206 points	▇ 3.6%	blunt
Decision Index 0.4.1: private new domains (equated points)	9.1800 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 15/247	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/tardellirs ↗

$ 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		= 26.8

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	54.2%	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]	47.4%	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