whatmodel.sh / decision / JPT-0.8B Qwen3.5-0.8B LoRA

JPT-0.8B Qwen3.5-0.8B LoRA

+ contribute

JPT-0.8B Qwen3.5-0.8B LoRA is an open-weights decision model from kirp. Its published size is 0.87B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine jpt-0.8b; reported model JPT-0.8B Qwen3.5-0.8B LoRA. Type: LoRA; technique: autoregressive. Published checkpoint/base reference: 5921ae03fbaff98fcbe781c1ff3f1200dc897fd1. Implementation: https://github.com/tic-top/llm2jev. 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.

33.3±1.0#287 of 355 decision modelsfrom 56 benchmark results across 3 sources

$ how it compares

The decision models ranked either side of JPT-0.8B Qwen3.5-0.8B LoRA, out of 357 with a score, then more from kirp.

#	model	score	where	released
287	JEV Ettin 150M Elfsong	34±1	model files	2026-10-23
288	Valen-0.8B Valen	34±1	model files
289	JPT-0.8B Qwen3.5-0.8B LoRA kirp	33±1	model files
290	CLM v0.1 (JevBench mini) Contrastive-LM	33±2	source code
291	Laya (typed-decisions) (JevBench mini) Convai Innovations	33±2	source code
	more from kirp
128	JPT-35B-A3B kirp	58±1	model files
178	JPT-9B Qwen3.5-9B LoRA kirp	54±1	model files
204	JPT-4B Qwen3.5-4B LoRA kirp	50±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▃▃▄▆██▆ #209 of 250 · 8.8% 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, Crivo-32M v2, Mola-68M 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	76.7% ✎	▁▂▁▁▁▃▂▄▅▆█▁ beats 40/246	very easy · avg 92%	▇▇ 5.0%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	30.1% ✎	▁▁▁▁▁▁▃▂▃▂█▂ beats 23/236	easy · avg 70%	▇ 2.0%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	50.0% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 41/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	52.8% ✎	▁▁▁▁▁·▁▁▃▄█▁ beats 37/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 42/243	medium · avg 37%	▇ 0.2%	sharp · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	64.1% ✎	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▁▁▁·▁▁▃▁▃▃█▅ #225 of 258 · 4.3% of its score · 7 tests

Beats mini-jev Qwen3-4B (decision readout), EXAONE-4.0-1.2B-JEV v0.3, Sieve 2B 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	30.1% ✎	▁▁▁▁▁▁▂▃▃▃█▅ beats 35/246	medium · avg 47%	▇ 1.3%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	32.8% ✎	▁▁▁▁▁▁▁▂▃▄▇█ beats 59/246	medium · avg 38%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	10.5% ✎	▁▁▁▁▃▁▁▂▃▆█▄ beats 11/238	easy · avg 83%	▇ 0.5%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	54.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 23/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	52.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 57/245	easy · avg 70%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	35.4% ✎	▁·▁▁▁▁▃▁▂█▇█ beats 12/238	easy · avg 79%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	49.1% ✎	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▂▂▃▃▂▅▆▃█▆▄▃ #224 of 256 · 22% of its score · 9 tests

Beats Valen-0.8B here, though they rank higher overall. Trails JEV Ettin 400M, LiquidAI d1-omni-600M, Dinah-1 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	48.6% ✎	▂▄▃▂▄▇▃▇█▅▃▁ beats 32/246	very easy · avg 85%	▇▇▇▇ 8.8%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	62.8% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 52/246	easy · avg 74%	▇▇ 4.8%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	38.6% ✎	▁▂▃▅▅█▂····▁ beats 33/246	medium · avg 60%	▇ 3.6%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	26.6% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 45/246	medium · avg 44%	▇ 1.2%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	72.7% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 93/246	easy · avg 71%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	78.1% ✎	▁···▁▁▁▁▃▆█▃ beats 63/246	easy · avg 84%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	44.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 55/246	medium · avg 62%	▇ 0.7%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	55.3% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 65/246	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	7.3% ✎	▁··▂▃▃▅▇█▇▃▃ beats 39/246	hard · avg 22%	▇ 0.3%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #229 of 247 · 6.7% of its score · 6 tests

Beats JEV Ettin 150M here, though they rank higher overall. Trails LFM2.5-350M-RLCD, system-one-gemma, Bekko System One v0 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	40.2% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 35/246	medium · avg 61%	▇ 2.8%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	50.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 15/246	easy · avg 83%	▇ 1.6%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	52.2% ✎	▁·▁▃▃▂▅█▄▂▁▁ beats 41/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	52.9% ✎	▁········▁▇█ beats 44/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	39.4% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 54/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	2.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 53/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▂▂▂▃▃▃▅▅▆█▂ #211 of 263 · 44% 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 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	68.1% ✎	▂▂▂▂▃▂▁▃▄▆█▆ beats 50/246	very easy · avg 90%	▇▇▇▇ 9.4%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	84.8% ✎	▁▁▂▁▂▃▂▂▃▆█▅ beats 50/246	very easy · avg 96%	▇▇▇▇ 9.3%	sharp · noisy
Decision Index 0.4.1: MMLU (accuracy) submitted	50.2% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 55/246	easy · avg 70%	▇▇ 6.1%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	45.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 53/246	easy · avg 66%	▇▇ 4.9%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	28.0% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 58/246	medium · avg 46%	▇▇ 4.8%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	53.2% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 26/246	easy · avg 78%	▇ 3.2%	at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	30.1% ✎	▂▆▅▅▆█▆▃▁··▁ beats 60/246	medium · avg 39%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	21.0% ✎	▁··▄█▆▆▆▅▅▃▁ beats 44/246	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	47.6% ✎	▁▁▃█▅▄▁▁▁▁▁▁ beats 24/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	54.4% ✎	▁███▆▅▃▃▁▁▁▁ beats 37/246	easy · avg 71%	▇ 0.8%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	33.9% ✎	██▄▃▃▄▁▁···▁ beats 20/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	3.9% ✎	▁▁▁▁▃▁▁▂▅█▂▁ beats 31/246	hard · avg 22%	▇ 0.5%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.5% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 31/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	17.2% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 234/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #77 of 79 · 8.6% of its score · 14 tests

Trails LiquidAI d1-omni-600M here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted	37.9200 points ✎	▁·▃▁▃▁▄▄▃▅█▂ beats 1/61	avg 63.423 points	▇ 1.0%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	8.6400 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 7/61	avg 22.797 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	48.0000 points ✎	▁·▁▁▃▁·▂▁▃▅█ beats 4/61	avg 66.987 points	▇ 0.8%	blunt
Decision Index Vision 0.4: private same skills (points)	39.6500 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 8/61	avg 48.067 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	12.7800 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 4/61	avg 28.443 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	40.9000 points ✎	▁·▂▃▁▃▃▅▅▃▂█ beats 5/61	avg 53.651 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	52.1300 points ✎	▂▁▁▁▃▃▁▅▅▆██ beats 7/61	avg 62.137 points	▇ 0.6%	blunt
Benchmark Heaven imagejevbench v0.3.0: intelligence (points)	20.4185 points ✎	▃·▃▃··▅█▅▅·▃ beats 2/12	avg 32.235 points	▇ 0.6%	blunt

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	74.8600 points ✎	▁·▁▃▁▁▃▁▂▂▅█ beats 7/61	avg 83.859 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted	13.7300 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 8/61	avg 19.676 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	33.6300 points ✎	▁···▁▃▂▂█▄▂▃ beats 6/61	avg 44.994 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	51.1900 points ✎	▃▁▁▁▂▁▁▁▄█▃▃ beats 1/61	avg 67.662 points	▇ 0.4%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	73.8900 points ✎	▁··▃▁▁▁▁▂▄█▁ beats 2/61	avg 85.184 points	▇ 0.3%	blunt
Benchmark Heaven imagejevbench v0.3.0: calibration (points)	71.7184 points ✎	▃···▃·▅█▅▃▃▅ beats 6/12	avg 68.584 points	▇ 0.3%	blunt

other tests2 not in a task · 5.2% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	16.9700 points ✎	▂▂▃▃▃▃▄▅▅▇█▃ beats 30/247	avg 41.206 points	▇ 3.4%	blunt
Decision Index 0.4.1: private new domains (equated points)	13.2000 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 42/247	avg 38.861 points	▇ 1.9%	blunt

$ where to run it

Download model files ↗
Published model files verified. This is the revision recorded by the benchmark. 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/kirp ↗

$ how the score was worked out · Decision Index 0.4.1 91%, Decision Index Vision 0.4 8%, Benchmark Heaven (own decisio… 1%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 91%	CC BY 4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇ 8%	CC BY 4.0
Benchmark Heaven (own decision evaluations)	2	▇ 1%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 33.3

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	64.1%	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]	49.1%	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