whatmodel.sh / decision / AJev lm6q (Gemma 4 31B)

AJev lm6q (Gemma 4 31B)

+ contribute

AJev lm6q (Gemma 4 31B) is an open-weights decision model from andyzhang232. Its published size is 31.27B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine ajev-lm6q; reported model AJev lm6q (Gemma 4 31B). 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.

68.6±1.5#27 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of AJev lm6q (Gemma 4 31B), out of 357 with a score, then more from andyzhang232.

#	model	score	where	released
25	vLLM-SR d3 (27B) vLLM Semantic Router	69±1	model files
26	Amos 1 Large (27B) mukaddamzaid	69±1	model files	2026-09-30
27	AJev lm6q (Gemma 4 31B) andyzhang232	69±2	model files
28	AnyJev Tacitus 31B morriszjm	69±2	model files
29	StartLux-Decision v1.1 9B StartLux	68±1	model files
	more from andyzhang232
109	AJev lora1 (Gemma 4 26B-A4B) andyzhang232	60±1	model files
130	AJev lora7 (Gemma 4 12B) andyzhang232	58±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #26 of 250 · 5.5% of its score · 6 tests

Beats Jeffan-31b-1710, Fastino GLiDE 1.2, KnowLine 31B Gen1 here, though they rank higher overall. Trails Solomon v1.1, Clef-flash, Clef-omni 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	85.2% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 169/236	easy · avg 70%	▇ 1.6%	sharp · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	65.1% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 135/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	80.7% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 193/243	medium · avg 37%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	86.1% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 178/246	easy · avg 72%	▇ 0.9%	noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.8% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 220/246	very easy · avg 92%	▇ 0.8%	sharp · maxed out · noisy
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▁▁▁·▁▁▁▁▃▃█▅ #47 of 258 · 8.0% of its score · 7 tests

Beats H2O Lightning 31B v1.1, AutoTrust-JEV-27B v1.1, MISA AI 2.0 Decision Plus · oak 1.1 (31B) here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, Standard One 8B SH (v4), StartLux-Decision v1.1 2B 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	46.7% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 175/246	medium · avg 38%	▇ 3.3%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	59.0% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 204/246	medium · avg 47%	▇ 2.9%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	83.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 175/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	86.6% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 198/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	80.7% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 104/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	92.4% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 164/238	easy · avg 83%	▇ 0.3%	sharp · maxed out · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	0.4% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #93 of 256 · 21% of its score · 9 tests

Beats Turion Jev 31B 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	79.2% ✎	▁▂▃▅▅█▃····▁ beats 230/246	medium · avg 60%	▇▇ 5.5%	typical
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	86.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 224/246	easy · avg 74%	▇▇ 5.1%	typical
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	71.7% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 240/246	medium · avg 44%	▇ 2.9%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	93.0% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 157/246	very easy · avg 85%	▇ 2.6%	sharp · maxed out
Decision Index 0.4.1: ACOS (per-review F1) submitted	32.4% ✎	▁··▂▃▃▅▇█▇▃▃ beats 173/246	hard · avg 22%	▇ 2.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	82.2% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 243/246	medium · avg 62%	▇ 1.1%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	77.5% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 137/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	81.0% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 191/246	easy · avg 66%	▇ 0.7%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	90.2% ✎	▁···▁▁▁▁▃▆█▃ beats 149/246	easy · avg 84%	▇ 0.5%	maxed out · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #52 of 247 · 10% of its score · 6 tests

Beats vLLM-SR d3-turbo v1.1 (27B), Perplexity Decider v1.2 (27B), OneJev1.6-27B here, though they rank higher overall. Trails Kas 4B, baselabs joey-1 (2B), Clef-flash 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	83.0% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 236/246	medium · avg 61%	▇▇ 4.0%	typical
Decision Index 0.4.1: Humicroedit (accuracy) submitted	68.1% ✎	▁·▁▃▂▂▅█▄▃▁▁ beats 231/246	medium · avg 60%	▇ 2.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	65.6% ✎	▁········▁▇█ beats 197/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	70.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 196/237	hard · avg 21%	▇ 1.4%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	95.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 196/246	easy · avg 83%	▇ 0.8%	sharp · maxed out · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	44.0% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 120/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #25 of 263 · 43% of its score · 14 tests

Beats KnowLine 35B-A3B Gen1.5, Bespoke Nimble v4 Max (27B), vera-large here, though they rank higher overall. Trails d1 (hosted), Jev 1.13, oenogarum (Gemma 4 31B) 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	72.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 221/246	medium · avg 46%	▇▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	83.5% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 210/246	easy · avg 66%	▇▇ 5.7%	typical
Decision Index 0.4.1: MMLU (accuracy) submitted	88.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 226/246	easy · avg 70%	▇▇ 5.6%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	53.6% ✎	▂▆▅▅▆█▆▃▁··▁ beats 225/246	medium · avg 39%	▇▇ 4.3%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	88.2% ✎	▁··▄█▆▆▆▅▅▃▁ beats 240/246	medium · avg 45%	▇ 3.7%	sharp · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	88.0% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 182/246	easy · avg 78%	▇ 2.6%	typical
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	34.3% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 196/246	hard · avg 22%	▇ 2.3%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.3% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 211/246	very easy · avg 90%	▇ 1.6%	sharp · maxed out

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	68.6% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 204/246	medium · avg 60%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	89.3% ✎	██▄▃▃▄▁▁···▁ beats 238/246	medium · avg 58%	▇ 1.2%	noisy
Decision Index 0.4.1: ChessBench (accuracy) submitted	27.7% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 233/246	hard · avg 16%	▇ 1.1%	blunt
Decision Index 0.4.1: CLadder (accuracy) submitted	80.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 178/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.2% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 220/246	very easy · avg 96%	▇ 0.6%	sharp · maxed out · noisy
Decision Index 0.4.1: HLE (accuracy) submitted	12.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 122/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 11% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	63.0500 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 232/247	avg 41.206 points	▇▇▇ 7.2%	blunt
Decision Index 0.4.1: private new domains (equated points)	74.3400 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 237/247	avg 38.861 points	▇▇ 4.0%	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		= 68.6

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]	0.4%	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