whatmodel.sh / decision / AJev lora7 (Gemma 4 12B)

AJev lora7 (Gemma 4 12B)

+ contribute

AJev lora7 (Gemma 4 12B) is an open-weights decision model from andyzhang232. Its published size is 11.96B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine ajev-lora7; reported model AJev lora7 (Gemma 4 12B). Type: LoRA; 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.

58.0±1.3#128 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of AJev lora7 (Gemma 4 12B), out of 357 with a score, then more from andyzhang232.

#	model	score	where	RAM	released
128	JPT-35B-A3B kirp	58±1	model files
129	Mica v0.5 4B akivet	58±1	model files		2026-10
130	AJev lora7 (Gemma 4 12B) andyzhang232	58±1	model files
131	Winnow-12B (DecisionBench b6ac22b0) EldanRing	58±2	local	~16GB
132	deepseek-v4.1-flash (DecisionBench openrout) DeepSeek	58±2	model files
	more from andyzhang232
27	AJev lm6q (Gemma 4 31B) andyzhang232	69±2	model files
109	AJev lora1 (Gemma 4 26B-A4B) andyzhang232	60±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #77 of 250 · 7.1% of its score · 6 tests

Beats Sieve 27B v2, allec-oavg (Gemma 4 31B), Jev 1.13 here, though they rank higher overall. Trails baselabs joey-1 (2B), Hopper 12B (trained), Solomon v1.1 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	58.3% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 67/236	easy · avg 70%	▇ 2.2%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	96.7% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 171/246	very easy · avg 92%	▇ 1.6%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	44.3% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 123/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	86.4% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 183/246	easy · avg 72%	▇ 1.1%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	65.2% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 141/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.9% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #98 of 258 · 6.8% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Decider 31B (NVFP4), Quyet-1.0-Large here, though they rank higher overall. Trails Jev-Style 2B v4, Sieve 2B v3, StartLux-Decision v1.1 0.8B 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	47.1% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 182/246	medium · avg 38%	▇ 2.6%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	55.1% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 152/246	medium · avg 47%	▇ 2.4%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	82.6% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 169/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	77.8% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 162/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	88.8% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 109/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	80.7% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 106/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	11.0% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #103 of 256 · 23% of its score · 9 tests

Beats jev-brain · Gemma-4-31B (decision readout), AnyJev L0 · Gemma-4-31B (decision readout), decisio 0.6.0 (Gemma 4 31B) (decision readout) here, though they rank higher overall. Trails Decider 4B, jiwo 4B v2, Sieve 4B 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	67.4% ✎	▁▂▃▅▅█▂····▁ beats 140/246	medium · avg 60%	▇▇ 5.4%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	79.6% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 149/246	easy · avg 74%	▇▇ 5.3%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	92.7% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 152/246	very easy · avg 85%	▇▇ 4.5%	sharp
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	71.5% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 239/246	medium · avg 44%	▇ 2.5%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	23.9% ✎	▁··▂▃▃▅▇█▇▃▃ beats 134/246	hard · avg 22%	▇ 1.3%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	79.5% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 157/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	79.7% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 221/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	80.4% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 183/246	easy · avg 66%	▇ 0.8%	at its level · noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	82.5% ✎	▁···▁▁▁▁▃▆█▃ beats 82/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #85 of 247 · 10% of its score · 6 tests

Beats Jev 1.13, jev-brain · Gemma-4-31B (decision readout), Jeffan-4B-2010 here, though they rank higher overall. Trails Amber 0.4B, Crivo-1B, GLiClass v4 edge (0.4B) 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	76.9% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 204/246	medium · avg 61%	▇▇ 4.0%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	65.1% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 208/246	medium · avg 60%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	63.1% ✎	▁········▁▇█ beats 147/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	91.5% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 161/246	easy · avg 83%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: POP909-CL (accuracy) submitted	9.8% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 102/237	hard · avg 21%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	44.6% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 127/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #114 of 263 · 44% of its score · 14 tests

Beats OneJev1.6-4B, Seb-9B v2, Mica v0.5 4B here, though they rank higher overall. Trails PurpleMIST-Flash-1.0, Jevfire Qwen3.8-27B (decision readout), JevK5 9B v0.3.3 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	56.1% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 140/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	77.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 139/246	easy · avg 70%	▇▇▇ 6.8%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	74.8% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 155/246	easy · avg 66%	▇▇▇ 6.3%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	56.9% ✎	▁··▄█▆▆▆▅▅▃▁ beats 152/246	medium · avg 45%	▇ 3.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	42.4% ✎	▂▆▅▅▆█▆▃▁··▁ beats 129/246	medium · avg 39%	▇ 3.4%	blunt · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	94.5% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 134/246	very easy · avg 90%	▇ 3.2%	sharp · maxed out
Decision Index 0.4.1: WinoGrande (accuracy) submitted	84.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 157/246	easy · avg 78%	▇ 3.0%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	38.0% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 217/246	hard · avg 22%	▇ 1.6%	at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.3% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 145/246	very easy · avg 96%	▇ 1.5%	sharp · maxed out · noisy
Decision Index 0.4.1: MuSR (accuracy) submitted	63.8% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 165/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	58.3% ✎	██▄▃▃▄▁▁···▁ beats 138/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	70.4% ✎	▁███▆▅▃▃▁▁▁▁ beats 127/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	15.9% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 121/246	hard · avg 16%	▇ 0.7%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	10.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 58/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 8.8% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	50.0400 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 147/247	avg 41.206 points	▇▇ 5.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	47.2000 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 149/247	avg 38.861 points	▇ 3.1%	blunt

$ where to run it

Download model files ↗
Published model files verified. Includes adapters or readout weights; follow the model documentation for the required base model. 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/andyzhang232 ↗

$ 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		= 58.0

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.9%	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]	11.0%	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