whatmodel.sh / decision / LFM2.5-350M-RLCD

LFM2.5-350M-RLCD

+ contribute

LFM2.5-350M-RLCD is an open-weights decision model from notnotsamuel. Its published size is 0.35B parameters. Licence: other.

Catalogue identity notes

Exact Decision Index tested engine lfm350-sdpa; reported model LFM2.5-350M-RLCD. Type: full fine-tune; 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.

15.8±1.1#352 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of LFM2.5-350M-RLCD, out of 357 with a score.

#	model	score	where	released
352	KaLM-Reranker-V1-Nano-R2 (DecisionBench 3902d645) KaLM-Embedding	17±2	model files
353	Nirnaya 0.4B kshitijthakkar	16±1	model files	2026-10-06
354	LFM2.5-350M-RLCD notnotsamuel	16±1	model files
355	Zev (decision readout) bhubbard	15±1	source code
356	gte-reranker-modernbert-base (DecisionBench f7481e60) Alibaba	7±2	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #240 of 250 · 10% of its score · 6 tests

Beats DM-JEPA 1.1, Von 1.3, Bekko System One v0 68M 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	38.4% ✎	▁▃▁▁▁▂▂▄▅▆█▁ beats 10/246	very easy · avg 92%	▇▇▇ 7.1%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	2.4% ✎	▁▁▃▁▁▁▁▂▃▂█▂ beats 6/236	easy · avg 70%	▇ 1.4%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	15.3% ✎	▃▁▁▂▃▅▅▆█▇█▃ beats 2/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	12.3% ✎	▁▃▁▁▁·▁▁▁▄█▁ beats 3/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 21/243	medium · avg 37%	▇ 0.1%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	50.3% ✎	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▁▁▃·▁▁▁▁▃▃█▅ #255 of 258 · 4.8% of its score · 7 tests

Beats JevK5 Lite, Qwen-2.5-1B-RLCD (decision readout), CLM-v0.1-8B Qwen3-8B heads here, though they rank higher overall. Trails Zev (decision readout) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	12.4% ✎	▁▁▁▃▁▁▂▂▃▃█▅ beats 4/246	medium · avg 47%	▇ 1.2%	typical
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	11.0% ✎	▁▃▁▁▁▁▁▂▂▄▇█ beats 6/246	medium · avg 38%	▇ 1.2%	blunt
Decision Index 0.4.1: HoVer (accuracy) submitted	50.1% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 2/246	easy · avg 74%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	0.3% ✎	▃▁▁▁▁▁▁▂▃▆█▄ beats 2/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	50.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 12/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	0.2% ✎	▃·▁▁▁▁▁▁▂█▇█ beats 2/238	easy · avg 79%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	34.2% ✎	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▃▂▂▃▂▅▆▃█▆▄▃ #253 of 256 · 23% of its score · 9 tests

Beats Prumo (rule-based engine), Nirnaya 0.4B here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: HellaSwag (accuracy) submitted	25.1% ✎	▃▄▂▂▄▇▃▇█▅▃▁ beats 3/246	very easy · avg 85%	▇▇▇ 8.5%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	42.9% ✎	▁▁▃▂▂▃▃▄▇▇█▄ beats 7/246	easy · avg 74%	▇▇ 6.1%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	19.6% ✎	▃▂▃▅▅█▂····▁ beats 3/246	medium · avg 60%	▇ 3.5%	typical
Decision Index 0.4.1: FinEntity (macro-F1) submitted	33.1% ✎	▁···▁▁▃▁▃▆█▃ beats 8/246	easy · avg 84%	▇ 1.2%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	20.2% ✎	▁▁▃▁▁▁▁▂▂▇▇█ beats 5/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	24.9% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 34/246	medium · avg 44%	▇ 0.9%	typical
Decision Index 0.4.1: VAST (macro-F1) submitted	25.3% ✎	▁▃▁▂▅▄▄▂▄▆█▄ beats 4/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	51.9% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 55/246	easy · avg 66%	▇ 0.6%	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	3.1% ✎	▁··▃▃▃▅▇█▇▃▃ beats 7/246	hard · avg 22%	▇ 0.2%	too hard for it · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #200 of 247 · 7.4% of its score · 6 tests

Beats vLLM-SR d3-nano (2B), Valen-4B, Saracura PT-BR 4B 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	18.8% ✎	▃▁▂▃▃▃▇▅█▅▃▁ beats 1/246	medium · avg 61%	▇ 2.6%	typical
Decision Index 0.4.1: BPoMP (accuracy) submitted	58.5% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 48/246	easy · avg 83%	▇ 2.0%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	49.6% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 17/246	medium · avg 60%	▇ 1.6%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	48.1% ✎	▁········▃▇█ beats 4/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	30.4% ✎	▃▂▄█▇▅▁▁▄▄▁▁ beats 3/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	5.1% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 72/237	hard · avg 21%	▇ 0.0%	sharp · too hard for it · noisy

knowledge & reasoning▃▂▂▂▂▃▃▅▅▆█▂ #262 of 263 · 47% of its score · 14 tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	26.5% ✎	▃▁▂▁▂▂▂▂▃▆█▅ beats 3/246	very easy · avg 96%	▇▇▇▇▇▇ 15%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	23.0% ✎	▃▂▂▂▂▂▁▃▄▆█▆ beats 0/246	very easy · avg 90%	▇▇▇▇ 9.0%	sharp
Decision Index 0.4.1: MMLU (accuracy) submitted	23.9% ✎	▃▄▄▃▃▂▅▇▅█▇▁ beats 1/246	easy · avg 70%	▇▇ 5.6%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	30.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 1/246	easy · avg 66%	▇▇ 4.6%	typical
Decision Index 0.4.1: WinoGrande (accuracy) submitted	52.0% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 19/246	easy · avg 78%	▇▇ 4.1%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	11.7% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 4/246	medium · avg 46%	▇ 3.0%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	27.0% ✎	▂▆▅▅▆█▆▃▁··▁ beats 36/246	medium · avg 39%	▇ 1.7%	blunt
Decision Index 0.4.1: MuSR (accuracy) submitted	36.2% ✎	▃▁▂█▅▄▁▁▁▁▁▁ beats 4/246	medium · avg 60%	▇ 1.0%	blunt · at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: CLadder (accuracy) submitted	49.7% ✎	▁███▆▅▃▃▁▁▁▁ beats 7/246	easy · avg 71%	▇ 1.0%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	18.0% ✎	▁··▄█▆▆▆▅▅▃▁ beats 13/246	medium · avg 45%	▇ 0.9%	sharp
Decision Index 0.4.1: CRUXEval (accuracy) submitted	32.3% ✎	██▄▃▃▄▁▁···▁ beats 10/246	medium · avg 58%	▇ 0.7%	noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	1.3% ✎	▁▁▃▁▁▁▁▂▅█▂▁ beats 17/246	hard · avg 22%	▇ 0.3%	too hard for it
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.0% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 23/246	hard · avg 16%	▇ 0.2%	blunt · too hard for it
Decision Index 0.4.1: HLE (accuracy) submitted	13.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 162/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 6.6% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	1.2700 points ✎	▃▂▂▃▃▃▄▅▅▇█▃ beats 1/247	avg 41.206 points	▇▇ 4.3%	blunt
Decision Index 0.4.1: private new domains (equated points)	12.7500 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 40/247	avg 38.861 points	▇ 2.4%	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/notnotsamuel ↗

$ 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		= 15.8

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	50.3%	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]	34.2%	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