whatmodel.sh / decision / Saracura PT-BR 4B

Saracura PT-BR 4B

+ contribute

Saracura PT-BR 4B is an open-weights decision model from Felhen. Its published size is 4.66B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine saracura-ptbr-4b; reported model Saracura PT-BR 4B. Type: LoRA + head; 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.

46.4±1.2#232 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Saracura PT-BR 4B, out of 357 with a score.

#	model	score	where
232	decider-2b v10 (JevBench mini) Mapika	47±2	source code
233	Jev-Style 2B v4 chaoliangUNSW	47±1	model files
234	Saracura PT-BR 4B Felhen	46±1	model files
235	LatentMesh Blitz 2B v1 LatentMesh Labs	46±1	request access
236	Winnow-E4B EldanRing	46±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #172 of 250 · 8.4% of its score · 6 tests

Beats LiquidAI d1-3B, Decider 4B, Together Tev1 Qwen3.5-4B here, though they rank higher overall. Trails JevK5 Lite, Mola-150M, Gevva E2B 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	90.8% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 78/246	very easy · avg 92%	▇ 3.1%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	52.6% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 55/236	easy · avg 70%	▇ 2.5%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	60.9% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 69/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	63.7% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 113/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	18.2% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 83/243	medium · avg 37%	▇ 0.8%	sharp · at its level · 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▁▁▁·▁▁▁▁▃▃█▅ #188 of 258 · 5.7% of its score · 7 tests

Beats JevK5 9B v0.3.3, JevK5 v0.3, Hopper (G) 1.2 Qwen3.5-4B LoRA here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA, Mola-68M, Bosun v3.1 1.7B LoRA 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	41.0% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 107/246	medium · avg 38%	▇ 1.9%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	42.2% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 70/246	medium · avg 47%	▇ 1.9%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	61.3% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 59/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	61.2% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 89/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	79.4% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 63/238	easy · avg 83%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	81.6% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 109/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	54.9% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #176 of 256 · 24% of its score · 9 tests

Beats Nari Decision 4B v3.2, StartLux-Decision v1.1 0.8B, InternLM Intern-Decision Qwen3.5-4B here, though they rank higher overall. Trails DecisionTune 1.0, jdi-ptr14-0.8b, FLock this-that 1.2 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	78.9% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 79/246	very easy · avg 85%	▇▇▇ 7.4%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	75.4% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 102/246	easy · avg 74%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	47.4% ✎	▁▂▃▅▅█▂····▁ beats 55/246	medium · avg 60%	▇▇ 4.9%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	41.8% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 96/246	medium · avg 44%	▇ 1.9%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	65.5% ✎	▁▁▁▁▁▁▁▂▃▇▇█ beats 61/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	49.1% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 73/246	medium · avg 62%	▇ 0.9%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	86.6% ✎	▁···▁▁▁▁▃▆█▃ beats 109/246	easy · avg 84%	▇ 0.8%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	71.6% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 105/246	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: ACOS (per-review F1) submitted	12.7% ✎	▁··▂▃▃▅▇█▇▃▃ beats 72/246	hard · avg 22%	▇ 0.8%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #213 of 247 · 8.5% of its score · 6 tests

Beats Valen-4B here, though they rank higher overall. Trails LFM2.5-350M-RLCD, system-one-gemma, Qwen-2.5-1B-RLCD (decision readout) 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	56.6% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 79/246	medium · avg 61%	▇ 3.7%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	52.5% ✎	▁·▁▃▃▂▅█▄▂▁▁ beats 42/246	medium · avg 60%	▇ 1.6%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	52.4% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 34/246	easy · avg 83%	▇ 1.4%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	58.8% ✎	▁········▁▇█ beats 91/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	2.1% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 46/237	hard · avg 21%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	42.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 104/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #156 of 263 · 46% of its score · 14 tests

Beats StartLux-Decision v1.1 2B, Solomon v1.1, Standard One 3B SH (v4) here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	51.6% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 118/246	medium · avg 46%	▇▇▇ 8.5%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	72.6% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 107/246	easy · avg 70%	▇▇▇ 7.4%	sharp · at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	92.0% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 106/246	very easy · avg 90%	▇▇▇ 6.5%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	61.0% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 86/246	easy · avg 66%	▇▇▇ 6.3%	at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	97.3% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 106/246	very easy · avg 96%	▇▇ 4.1%	sharp · maxed out · noisy
Decision Index 0.4.1: WinoGrande (accuracy) submitted	69.1% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 74/246	easy · avg 78%	▇ 3.4%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	44.0% ✎	▁··▄█▆▆▆▅▅▃▁ beats 124/246	medium · avg 45%	▇ 2.8%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	40.3% ✎	▂▆▅▅▆█▆▃▁··▁ beats 112/246	medium · avg 39%	▇ 2.5%	blunt · 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	56.5% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 90/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	48.6% ✎	██▄▃▃▄▁▁···▁ beats 104/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	18.4% ✎	▁▁▁▁▁▁▁▃▅█▂▁ beats 68/246	hard · avg 22%	▇ 0.9%	typical
Decision Index 0.4.1: CLadder (accuracy) submitted	62.3% ✎	▁███▆▅▃▃▁▁▁▁ beats 74/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	10.2% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 61/246	hard · avg 16%	▇ 0.5%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	9.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 19/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 7.0% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	34.3200 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 75/247	avg 41.206 points	▇▇ 4.5%	blunt
Decision Index 0.4.1: private new domains (equated points)	34.6000 points ✎	▃█▃▃▃▆▃▃▄▄▄▄ beats 103/247	avg 38.861 points	▇ 2.5%	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/felhen-ai ↗

$ 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		= 46.4

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]	54.9%	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