whatmodel.sh / decision / Eikos-27B-FP8 Qwen3.8-27B LoRA

Eikos-27B-FP8 Qwen3.8-27B LoRA

+ contribute

Eikos-27B-FP8 Qwen3.8-27B LoRA is an open-weights decision model from caiovicentino1. Its published size is 27.78B parameters. Licence: mit.

Catalogue identity notes

Exact Decision Index tested engine eikos-27b-fp8; reported model Eikos-27B-FP8 Qwen3.8-27B LoRA. Type: LoRA; technique: autoregressive. Implementation: https://github.com/caiovicentino/eikos. 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.

59.4±1.3#115 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Eikos-27B-FP8 Qwen3.8-27B LoRA, out of 357 with a score.

#	model	score	where	released
114	simple-jev · Qwen3.8-27B (featherless) (decision readout) featherless-ai	60±1	source code
115	OneJev1.6-4B OmniJev	60±1	model files	2026-10-17
116	Eikos-27B-FP8 Qwen3.8-27B LoRA caiovicentino1	59±1	model files
117	JADE theunnecessarythings	59±1	model files	2026-10-01
118	xor (DecisionBench 679decd4) juspay	59±2	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #87 of 250 · 6.9% of its score · 6 tests

Beats Sieve 27B v2, Jev 1.13, Xor 26B-A4B v1.2 here, though they rank higher overall. Trails OneJev1.6-0.8B, Jev-Omni, baselabs joey-1 (2B) 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	86.0% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 195/236	easy · avg 70%	▇ 2.1%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	96.3% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 162/246	very easy · avg 92%	▇ 1.5%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	51.1% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 133/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	79.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 134/246	easy · avg 72%	▇ 1.0%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	66.8% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 181/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.7% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #94 of 258 · 7.0% 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	48.3% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 203/246	medium · avg 38%	▇ 2.7%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	55.5% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 159/246	medium · avg 47%	▇ 2.4%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	73.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 115/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	63.8% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 102/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	87.7% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 101/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	79.0% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 86/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	66.9% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #99 of 256 · 22% of its score · 9 tests

Beats Turion Jev 31B, FlexDM · Gemma-4-31B (decision readout), jev-brain · 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	75.6% ✎	▁▂▃▅▅█▂····▁ beats 200/246	medium · avg 60%	▇▇ 5.4%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	84.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 203/246	easy · avg 74%	▇▇ 5.3%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	93.0% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 156/246	very easy · avg 85%	▇▇ 4.2%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	57.4% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 171/246	medium · avg 44%	▇ 2.5%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	22.4% ✎	▁··▂▃▃▅▇█▇▃▃ beats 125/246	hard · avg 22%	▇ 1.4%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	71.3% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 144/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	80.4% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 168/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	74.1% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 124/246	easy · avg 66%	▇ 0.8%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	0.0% ✎	▃···▁▁▁▁▃▆█▃ beats 0/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #68 of 247 · 10% 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 Amber 0.4B, Crivo-1B, Kas 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	71.0% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 162/246	medium · avg 61%	▇▇ 4.0%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	61.0% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 119/246	medium · avg 60%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	65.2% ✎	▁········▁▇█ beats 184/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	28.6% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 148/237	hard · avg 21%	▇ 1.1%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	93.7% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 179/246	easy · avg 83%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	43.6% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 112/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #84 of 263 · 44% of its score · 14 tests

Beats StartLux-Decision v1.1 4B, KnowLine 4B Gen5.5, Jeffan-4B-2010 here, though they rank higher overall. Trails Solar Decide, Clef-flash, Decider chat · Qwen3.6-27B (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	61.0% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 162/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	84.2% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 181/246	easy · avg 70%	▇▇▇ 6.6%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	78.9% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 184/246	easy · avg 66%	▇▇▇ 6.3%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	43.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 122/246	medium · avg 45%	▇ 3.7%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	50.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 202/246	medium · avg 39%	▇ 3.5%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	84.1% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 152/246	easy · avg 78%	▇ 3.0%	typical
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	96.9% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 191/246	very easy · avg 90%	▇ 2.9%	sharp · maxed out
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	28.3% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 127/246	hard · avg 22%	▇ 1.7%	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	99.1% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 208/246	very easy · avg 96%	▇ 1.4%	sharp · maxed out · noisy
Decision Index 0.4.1: MuSR (accuracy) submitted	60.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 141/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	68.1% ✎	██▄▃▃▄▁▁···▁ beats 162/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	75.1% ✎	▁███▆▅▃▃▁▁▁▁ beats 158/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	17.2% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 133/246	hard · avg 16%	▇ 0.8%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	9.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 27/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 9.1% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	55.5200 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 173/247	avg 41.206 points	▇▇ 5.8%	blunt
Decision Index 0.4.1: private new domains (equated points)	63.6900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 199/247	avg 38.861 points	▇ 3.2%	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/caiovicentino1 ↗

$ 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		= 59.4

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.7%	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]	66.9%	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