whatmodel.sh / decision / reflex Qwen3.8-27B-FP8 (pmscr) (decision readout)

reflex Qwen3.8-27B-FP8 (pmscr) (decision readout)

+ contribute

reflex Qwen3.8-27B-FP8 (pmscr) (decision readout) is a source-available decision implementation from kshetrajna12. Its published size is 27.78B parameters.

Catalogue identity notes

Exact Decision Index tested engine reflex-27b-pmscr; reported model reflex Qwen3.8-27B-FP8 (pmscr). Type: inference technique; technique: autoregressive. Implementation: https://github.com/kshetrajna12/reflex. Comparison entry; no current run command, API price or speed inferred from the benchmark.

Model information sources

· Parameter count ↗

Publisher parameter count; includes the served backbone, not just adapter size.

60.6±1.3#105 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of reflex Qwen3.8-27B-FP8 (pmscr) (decision readout), out of 357 with a score, then more from kshetrajna12.

#	model	score	where	released
104	glm-5.3-flash (DecisionBench openrout) Z.ai	61±2	comparison only	2026-08-26
105	reflex-qwen3.5-4b-lora (DecisionBench 9df1cbbb) kshetrajna12	61±2	model files
106	reflex Qwen3.8-27B-FP8 (pmscr) (decision readout) kshetrajna12	61±1	source code
107	OneJev1.5-9B OmniJev	61±4	model files	2026-10-13
108	imajev-4b (DecisionBench c9e5f132) mohit67890	61±2	model files
	more from kshetrajna12
80	reflex-27b (DecisionBench 1d4bf0f2) kshetrajna12	63±2	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #44 of 250 · 6.7% of its score · 6 tests

Beats Fastino GLiDE 1.2, vLLM-SR d3-ultra (Decision 3.0, 27B), AutoTrust-JEV-27B v1.1 here, though they rank higher overall. Trails baselabs joey-1 (2B), Solomon v1.1, Clef-flash 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	85.4% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 178/236	easy · avg 70%	▇ 2.0%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	97.5% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 205/246	very easy · avg 92%	▇ 1.4%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	59.1% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 144/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	69.4% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 228/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy) submitted	81.2% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 151/246	easy · avg 72%	▇ 1.0%	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▁▁▁·▁▁▁▁▃▃█▅ #53 of 258 · 7.1% of its score · 7 tests

Beats H2O Lightning 31B v1.1, AutoTrust-JEV-27B v1.1, d1.1 (hosted) 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	49.5% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 225/246	medium · avg 38%	▇ 2.8%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	58.7% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 199/246	medium · avg 47%	▇ 2.5%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	74.4% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 119/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	86.1% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 194/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	90.2% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 132/238	easy · avg 83%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	79.3% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 88/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	25.0% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #79 of 256 · 22% 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: ANLI (macro-F1) submitted	73.9% ✎	▁▂▃▅▅█▂····▁ beats 189/246	medium · avg 60%	▇▇ 5.5%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	83.2% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 192/246	easy · avg 74%	▇▇ 5.3%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	93.9% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 171/246	very easy · avg 85%	▇▇ 4.0%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	57.7% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 172/246	medium · avg 44%	▇ 2.6%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	38.6% ✎	▁··▂▃▃▅▇█▇▃▃ beats 195/246	hard · avg 22%	▇ 1.5%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	72.8% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 152/246	medium · avg 62%	▇ 1.1%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	79.8% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 160/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	73.5% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 118/246	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	87.8% ✎	▁···▁▁▁▁▃▆█▃ beats 120/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #36 of 247 · 10% of its score · 6 tests

Beats Jeffan-31b-1710, vLLM-SR d3-turbo v1.1 (27B), Nace.AI Drex Max v1 (27B) here, though they rank higher overall. Trails Kas 4B, baselabs joey-1 (2B), Xor 1.2 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	72.4% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 168/246	medium · avg 61%	▇▇ 4.1%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	63.1% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 177/246	medium · avg 60%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	65.4% ✎	▁········▁▇█ beats 187/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	43.9% ✎	▄▅▅▃▆▅▃▅▃▅▃█ beats 164/237	hard · avg 21%	▇ 1.1%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	96.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 210/246	easy · avg 83%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	42.2% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 98/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #90 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, Xor 1.2 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	61.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 164/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	83.3% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 169/246	easy · avg 70%	▇▇▇ 6.5%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	69.3% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 129/246	easy · avg 66%	▇▇ 6.2%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	40.9% ✎	▁··▄█▆▆▆▅▅▃▁ beats 114/246	medium · avg 45%	▇ 3.7%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	48.0% ✎	▂▆▅▅▆█▆▃▁··▁ beats 177/246	medium · avg 39%	▇ 3.6%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	85.3% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 163/246	easy · avg 78%	▇ 2.9%	typical
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	97.3% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 213/246	very easy · avg 90%	▇ 2.7%	sharp · maxed out
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	28.7% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 128/246	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: MuSR (accuracy) submitted	65.2% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 179/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.0% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 189/246	very easy · avg 96%	▇ 1.2%	sharp · maxed out · noisy
Decision Index 0.4.1: CRUXEval (accuracy) submitted	65.6% ✎	██▄▃▃▄▁▁···▁ beats 157/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	67.6% ✎	▁███▆▅▃▃▁▁▁▁ beats 115/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	16.7% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 129/246	hard · avg 16%	▇ 0.8%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	12.2% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 117/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 9.3% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	57.0000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 187/247	avg 41.206 points	▇▇ 6.0%	blunt
Decision Index 0.4.1: private new domains (equated points)	61.4300 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 190/247	avg 38.861 points	▇ 3.3%	blunt

$ where to run it

Implementation and setup instructions ↗
Published implementation and setup documentation verified. This entry describes a decision readout or evaluated configuration, not necessarily separate trained weights. Follow the referenced version and model settings; hardware compatibility has not been verified. Source · checked 2026-10-31.

Model repository and documentation: github.com/kshetrajna12 ↗

$ 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		= 60.6

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]	25.0%	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