whatmodel.sh / decision / Amber Hybrid 4B (decision readout)

Amber Hybrid 4B (decision readout)

+ contribute

Amber Hybrid 4B (decision readout) is an open-weights decision model from MLukauskas. Its published size is 4.61B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine amber-hybrid-4b; reported model Amber Hybrid 4B. Type: inference technique; 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.

56.5±1.3#143 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Amber Hybrid 4B (decision readout), out of 357 with a score, then more from MLukauskas.

#	model	score	where	RAM	released
143	Jebadiah 9B v2.1 (T1e) frontier-infra	57±1	local	~25GB	2026-10
144	CoCo-Decision-4B 2.4 Corners	57±1	model files		2026-10-16
145	Amber Hybrid 4B (decision readout) MLukauskas	57±1	model files
146	Solar Decide Upstage	57±1	api price unknown		2026-09-22
147	Sieve-Vision-4B Sthānika AI	56±4	model files
	more from MLukauskas
157	Amber 4B MLukauskas	55±1	model files
274	Amber 0.4B MLukauskas	37±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #53 of 250 · 7.3% of its score · 6 tests

Beats vLLM-SR d3-ultra (Decision 3.0, 27B), AutoTrust-JEV-27B v1.1, OneShot 27B here, though they rank higher overall. Trails baselabs joey-1 (2B), 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	80.5% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 119/236	easy · avg 70%	▇ 2.2%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.3% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 192/246	very easy · avg 92%	▇ 1.8%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	94.3% ✎	█▁▁▃▄▄▆▄▁▃▁▃ beats 209/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	89.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 205/246	easy · avg 72%	▇ 1.1%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	71.1% ✎	▁▁▁▁▁·▁▁▁▄█▃ beats 239/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	72.2% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #95 of 258 · 6.7% 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	40.6% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 104/246	medium · avg 38%	▇ 2.5%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	55.1% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 151/246	medium · avg 47%	▇ 2.3%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	86.5% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 204/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	88.3% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 206/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	95.0% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 204/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	90.3% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 185/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	63.8% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #83 of 256 · 23% of its score · 9 tests

Beats Turion Jev 31B, AJev lm6q (Gemma 4 31B), oenogarum (Gemma 4 31B) here, though they rank higher overall. Trails Sieve 4B, Amber 4B, Decider 35B-A3B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	75.7% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 103/246	easy · avg 74%	▇▇ 5.4%	typical
Decision Index 0.4.1: ANLI (macro-F1) submitted	61.4% ✎	▁▂▃▅▅█▂····▁ beats 109/246	medium · avg 60%	▇▇ 5.4%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	93.9% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 172/246	very easy · avg 85%	▇▇ 4.9%	sharp
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	42.4% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 101/246	medium · avg 44%	▇ 2.4%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	45.2% ✎	▁··▂▃▃▅▇█▇▃▃ beats 215/246	hard · avg 22%	▇ 1.2%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	78.2% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 144/246	easy · avg 71%	▇ 1.1%	noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	78.4% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 203/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	77.8% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 154/246	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	94.6% ✎	▁···▁▁▁▁▃▆█▃ beats 229/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #63 of 247 · 9.5% of its score · 6 tests

Beats mogan-decision-31B-it, FlexDM · Gemma-4-31B (decision readout), Jev 1.13 here, though they rank higher overall. Trails Crivo-1B, Kas 4B, Aurelis-2B 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	70.8% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 158/246	medium · avg 61%	▇▇ 4.0%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	63.8% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 189/246	medium · avg 60%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	94.2% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 183/246	easy · avg 83%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	66.7% ✎	▁········▁▇█ beats 222/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	81.3% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 227/237	hard · avg 21%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	60.0% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 203/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #144 of 263 · 45% of its score · 14 tests

Beats Winnow-12B (DecisionBench b6ac22b0) here, though they rank higher overall. Trails razorback16 diffgemma (decision readout), Solar Decide Flash, mmastrac diffgemma (decision readout) 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	49.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 110/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	73.2% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 109/246	easy · avg 70%	▇▇▇ 6.9%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	71.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 144/246	easy · avg 66%	▇▇▇ 6.3%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	93.3% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 116/246	very easy · avg 90%	▇ 3.6%	sharp · maxed out
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	59.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 158/246	medium · avg 45%	▇ 3.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	36.2% ✎	▂▆▅▅▆█▆▃▁··▁ beats 87/246	medium · avg 39%	▇ 3.3%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	83.2% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 143/246	easy · avg 78%	▇ 3.1%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	97.9% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 121/246	very easy · avg 96%	▇ 1.8%	sharp · maxed out · noisy

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	42.4% ✎	▁▁▁▁▁▁▁▂▅█▃▁ beats 231/246	hard · avg 22%	▇ 1.5%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	57.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 101/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	53.9% ✎	██▄▃▃▄▁▁···▁ beats 128/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	82.8% ✎	▁███▆▅▃▃▁▁▁▁ beats 189/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	9.2% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 50/246	hard · avg 16%	▇ 0.7%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 75/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 8.5% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	49.9500 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 144/247	avg 41.206 points	▇▇ 5.5%	blunt
Decision Index 0.4.1: private new domains (equated points)	31.9300 points ✎	▃█▃▃▃▆▃▃▄▄▄▄ beats 96/247	avg 38.861 points	▇ 3.0%	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/MLukauskas ↗

$ 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		= 56.5

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	72.2%	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]	63.8%	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