whatmodel.sh / decision / Saina Helm 2.0 v2

Saina Helm 2.0 v2

+ contribute

Saina Helm 2.0 v2 is an open-weights decision model from Saina. Its published size is 0.85B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine saina-helm-2-v2; reported model Saina Helm 2.0 v2. Type: LoRA + head; 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.

39.4±1.1#265 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Saina Helm 2.0 v2, out of 357 with a score.

#	model	score	where
265	FLock this-that 1.2 FLock.io	40±1	model files
266	jdi-ptr14-0.8b AnamK	40±1	model files
267	Saina Helm 2.0 v2 Saina	39±1	model files
268	Valen-2B Valen	39±1	model files
269	Saina Helm 2 Omni (0.8B) Saina	39±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #149 of 250 · 9.1% of its score · 6 tests

Beats Cerno 4B v1.1, Trio-Spark DI (9B), Decider 35B-A3B here, though they rank higher overall. Trails JevK5 Lite, Amber 0.4B 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	92.5% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 99/246	very easy · avg 92%	▇▇ 4.3%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	81.7% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 125/236	easy · avg 70%	▇ 2.4%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	83.8% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 166/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	48.4% ✎	▁▁▁▁▁·▁▃▁▄█▁ beats 28/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	6.8% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 61/243	medium · avg 37%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	78.5% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #162 of 258 · 5.1% of its score · 7 tests

Beats Solar Decide, decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout), JevK5 9B v0.3.3 here, though they rank higher overall. Trails DecisionTune 1.0, jiwo 0.8B v2, Amber 0.4B 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	21.2% ✎	▁▁▁▁▁▃▁▂▂▄▇█ beats 21/246	medium · avg 38%	▇ 1.6%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	47.9% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 96/246	medium · avg 47%	▇ 1.6%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	82.0% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 164/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	92.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 168/238	easy · avg 83%	▇ 0.5%	sharp · at its level · noisy
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	50.9% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 45/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	91.0% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 197/238	easy · avg 79%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	43.9% ✎	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▂▂▂▃▃▅▆▃█▆▄▃ #204 of 256 · 24% of its score · 9 tests

Trails DecisionTune 1.0, vera-spark, JEV FLAN-T5 Large public v2 (342M) 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	65.5% ✎	▂▄▂▃▄▇▃▇█▅▃▁ beats 52/246	very easy · avg 85%	▇▇▇▇ 8.9%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	63.4% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 53/246	easy · avg 74%	▇▇ 5.3%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	48.2% ✎	▁▂▃▅▅█▂····▁ beats 58/246	medium · avg 60%	▇▇ 4.4%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	29.1% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 57/246	medium · avg 44%	▇ 1.5%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	85.4% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 230/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	74.8% ✎	▁···▁▁▁▁▃▆█▃ beats 56/246	easy · avg 84%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	69.5% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 135/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	77.5% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 151/246	easy · avg 66%	▇ 0.7%	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	37.3% ✎	▁··▂▃▃▅▇█▇▃▃ beats 190/246	hard · avg 22%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #193 of 247 · 7.8% of its score · 6 tests

Beats Kev 9B v2, vLLM-SR d3-nano (2B), Valen-4B 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	53.4% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 66/246	medium · avg 61%	▇ 3.4%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	60.8% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 54/246	easy · avg 83%	▇ 1.6%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	59.9% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 93/246	medium · avg 60%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	61.3% ✎	▁········▁▇█ beats 115/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	3.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 67/237	hard · avg 21%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	51.8% ✎	▁▂▄█▇▅▃▁▄▄▁▁ beats 180/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▃▃▃▅▅▆█▂ #208 of 263 · 47% of its score · 14 tests

Beats Crivo-1B, vLLM-SR vela3-fast (Vela 3.0, 0.4B), Decision-1.0-Eos-0.8B (DecisionBench 3c2d6326) here, though they rank higher overall. Trails laya (DecisionBench 1c5edc17), DM-JEPA 1.1, Strands Decider 2B (Hobson v21) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	71.7% ✎	▂▂▂▂▃▂▁▃▄▆█▆ beats 57/246	very easy · avg 90%	▇▇▇▇ 8.8%	sharp
Decision Index 0.4.1: MMLU (accuracy) submitted	49.2% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 52/246	easy · avg 70%	▇▇▇ 7.2%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	85.4% ✎	▁▁▂▁▂▃▂▂▃▆█▅ beats 52/246	very easy · avg 96%	▇▇▇ 7.0%	sharp · noisy
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	24.7% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 51/246	medium · avg 46%	▇▇▇ 6.7%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	42.9% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 44/246	easy · avg 66%	▇▇ 5.9%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	62.4% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 52/246	easy · avg 78%	▇ 3.5%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	34.6% ✎	▁··▄█▆▆▆▅▅▃▁ beats 90/246	medium · avg 45%	▇ 2.2%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	24.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 13/246	medium · avg 39%	▇ 2.1%	blunt · at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	54.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 66/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	76.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 164/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	30.9% ✎	██▄▃▃▄▁▁···▁ beats 5/246	medium · avg 58%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	14.2% ✎	▁▁▁▁▁▁▁▃▅█▂▁ beats 54/246	hard · avg 22%	▇ 0.7%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	21.8% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 184/246	hard · avg 16%	▇ 0.4%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	13.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 160/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 6.2% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	34.0000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 73/247	avg 41.206 points	▇▇ 4.0%	blunt
Decision Index 0.4.1: private new domains (equated points)	12.2100 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 36/247	avg 38.861 points	▇ 2.2%	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/run-saina ↗

$ 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		= 39.4

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	78.5%	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]	43.9%	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