Amber 0.4B

+ contribute

Amber 0.4B is an open-weights decision model from MLukauskas. Its published size is 0.4B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine amber-0.4b; reported model Amber 0.4B. Type: full fine-tune; technique: encoder. 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.

37.4±1.1#272 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Amber 0.4B, out of 357 with a score, then more from MLukauskas.

#	model	score	where	RAM	released
272	vLLM-SR Decision 2.0 Sol 2B vLLM Semantic Router	38±1	local	~11GB
273	Sieve 0.8B Sthānika AI	38±1	model files		2026-10-13
274	Amber 0.4B MLukauskas	37±1	model files
275	kev-0.6b (DecisionBench dece6dba) Jared Palmer	37±2	model files
276	jiwo 0.8B v2 eljiwo	37±1	model files		2026-10-10
	more from MLukauskas
145	Amber Hybrid 4B (decision readout) MLukauskas	57±1	model files
157	Amber 4B MLukauskas	55±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #132 of 250 · 9.3% of its score · 6 tests

Beats Tern-35B-A3B, Cerno 4B v1.1, Trio-Spark DI (9B) here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	93.9% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 116/246	very easy · avg 92%	▇▇ 4.7%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	78.9% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 113/236	easy · avg 70%	▇ 2.3%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	75.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 114/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	64.9% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 130/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	95.5% ✎	█▁▁▃▄▄▆▄▁▃▁▃ beats 214/243	medium · avg 37%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	68.8% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #142 of 258 · 5.0% of its score · 7 tests

Beats Quyet-1.0-Large, Decider chat · Qwen3.6-27B (decision readout), Sieve 9B v2 here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	51.8% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 115/246	medium · avg 47%	▇ 1.5%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	24.9% ✎	▁▁▁▁▁▁▃▂▂▄▇█ beats 30/246	medium · avg 38%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	91.5% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 149/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	86.3% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 198/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	88.4% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 207/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	90.2% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 182/238	easy · avg 79%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	51.6% ✎	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▂▂▂▃▃▅▆▃█▆▄▃ #203 of 256 · 24% of its score · 9 tests

Beats Saina Helm 2.0 v2, Valen-2B, Saina Helm 2 Omni (0.8B) here, though they rank higher overall. 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	71.7% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 54/246	very easy · avg 85%	▇▇▇▇ 9.2%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	63.6% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 55/246	easy · avg 74%	▇▇ 5.3%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	50.0% ✎	▁▂▃▅▅█▂····▁ beats 66/246	medium · avg 60%	▇▇ 4.3%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	35.2% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 73/246	medium · avg 44%	▇ 1.4%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	79.2% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 155/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	91.4% ✎	▁···▁▁▁▁▃▆█▃ beats 169/246	easy · avg 84%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	77.2% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 186/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	72.9% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 115/246	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	41.9% ✎	▁··▂▃▃▅▇█▇▃▃ beats 207/246	hard · avg 22%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #66 of 247 · 7.6% 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.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: New Yorker (accuracy) submitted	59.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 95/246	medium · avg 61%	▇ 3.3%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	93.9% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 180/246	easy · avg 83%	▇ 1.7%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	61.2% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 124/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	61.1% ✎	▁········▁▇█ beats 113/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	58.1% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 191/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	81.3% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 226/237	hard · avg 21%	▇ 0.2%	sharp · too hard for it · noisy

knowledge & reasoning▁▃▂▂▂▃▃▅▅▆█▂ #251 of 263 · 48% of its score · 14 tests

Trails CLM-v0.1-8B Qwen3-8B heads, Qwen-2.5-1B-RLCD (decision readout), GLiNER2.5-Decide 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	34.4% ✎	▂▃▂▂▂▂▁▃▄▆█▆ beats 12/246	very easy · avg 90%	▇▇▇▇ 9.4%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	50.6% ✎	▁▁▃▁▂▂▂▂▃▆█▅ beats 12/246	very easy · avg 96%	▇▇▇ 8.0%	sharp · noisy
Decision Index 0.4.1: MMLU (accuracy) submitted	29.8% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 6/246	easy · avg 70%	▇▇▇ 7.1%	sharp · at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	13.2% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 9/246	medium · avg 46%	▇▇ 6.2%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	61.5% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 88/246	easy · avg 66%	▇▇ 5.7%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	69.3% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 77/246	easy · avg 78%	▇ 3.5%	at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	26.0% ✎	▂▆▅▅▆█▆▃▁··▁ beats 28/246	medium · avg 39%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	17.3% ✎	▁··▄█▆▆▆▅▅▃▁ beats 4/246	medium · avg 45%	▇ 2.0%	sharp · 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	39.6% ✎	▃▁▂█▅▄▁▁▁▁▁▁ beats 12/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	83.0% ✎	▁███▆▅▃▃▁▁▁▁ beats 191/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	45.6% ✎	██▄▃▃▄▁▁···▁ beats 91/246	medium · avg 58%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	37.6% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 214/246	hard · avg 22%	▇ 0.6%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	9.3% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 52/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	17.4% ✎	▁▁▂▃▆█▇▅▅▃▃▁ beats 237/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 6.0% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	35.0900 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 77/247	avg 41.206 points	▇▇ 3.9%	blunt
Decision Index 0.4.1: private new domains (equated points)	12.3500 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 38/247	avg 38.861 points	▇ 2.1%	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 0.4.1 100%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 37.4

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	68.8%	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]	51.6%	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