whatmodel.sh / decision / MoganAI Lavoir ModernBERT-large

MoganAI Lavoir ModernBERT-large

+ contribute

MoganAI Lavoir ModernBERT-large is an open-weights decision model from Mogan AI. Its published size is 0.4B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Exact Decision Index tested engine lavoir; reported model MoganAI Lavoir ModernBERT-large. Type: full fine-tune; technique: encoder. Published checkpoint/base reference: 4c5eaeb99b2368f1416b9893c7aacc58235aa09f. Implementation: https://github.com/moganai/lavoir. 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.

23.5±1.0#333 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of MoganAI Lavoir ModernBERT-large, out of 357 with a score, then more from Mogan AI.

#	model	score	where
333	Crivo-17M tardellirs	24±1	model files
334	Bekko System One v0 68M hotchpotch	24±1	model files
335	MoganAI Lavoir ModernBERT-large Mogan AI	24±1	model files
336	GLiNER2.5-Decide Fastino	23±1	model files
337	Prumo (rule-based engine) tardellirs	23±1	source code
	more from Mogan AI
35	mogan-decision-31B-it Mogan AI	67±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #234 of 250 · 10% of its score · 6 tests

Beats DM-JEPA 1.1, JEV FLAN-T5 Large public v2 (342M), JEV Ettin 400M here, though they rank higher overall. Trails Qwen-2.5-1B-RLCD (decision readout), Prumo (rule-based engine), 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: BFCL (case exact accuracy) submitted	39.5% ✎	▁▃▁▁▁▂▂▄▅▆█▁ beats 16/246	very easy · avg 92%	▇▇▇ 6.7%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	28.3% ✎	▁▁▁▁▁▁▃▂▃▂█▂ beats 21/236	easy · avg 70%	▇ 1.7%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	23.4% ✎	▁▁▃▂▃▅▅▆█▇█▃ beats 10/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	27.7% ✎	▁▁▁▁▃·▁▁▁▄█▁ beats 14/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 30/243	medium · avg 37%	▇ 0.1%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	49.1% ✎	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▁▁▁·▁▁▃▁▃▃█▅ #233 of 258 · 4.5% of its score · 7 tests

Beats Sieve 2B, Strands Decider 2B (Hobson v21), DM-JEPA 1.1 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	28.1% ✎	▁▁▁▁▁▁▃▂▃▃█▅ beats 29/246	medium · avg 47%	▇ 1.2%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	16.7% ✎	▁▁▁▃▁▁▁▂▂▄▇█ beats 11/246	medium · avg 38%	▇ 1.2%	blunt
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	9.4% ✎	▁▁▁▁▃▁▁▂▃▆█▄ beats 10/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	59.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 46/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	50.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 13/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	28.0% ✎	▁·▁▁▁▁▃▁▂█▇█ beats 9/238	easy · avg 79%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	59.8% ✎	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▂▃▂▃▂▅▆▃█▆▄▃ #235 of 256 · 23% of its score · 9 tests

Beats Crivo-68M, Bosun v3.1 1.7B LoRA, Mola-68M here, though they rank higher overall. Trails 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: HellaSwag (accuracy) submitted	42.0% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 21/246	very easy · avg 85%	▇▇▇▇ 9.4%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	48.7% ✎	▁▁▁▃▂▃▃▄▇▇█▄ beats 13/246	easy · avg 74%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	36.9% ✎	▁▂▃▅▅█▂····▁ beats 29/246	medium · avg 60%	▇ 3.5%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	58.9% ✎	▁···▁▁▁▃▃▆█▃ beats 20/246	easy · avg 84%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	46.3% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 115/246	medium · avg 44%	▇ 1.0%	typical
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	30.1% ✎	▁▁▁▁▃▁▁▂▂▇▇█ beats 17/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	35.1% ✎	▁▁▁▃▅▄▄▂▄▆█▄ beats 15/246	medium · avg 62%	▇ 0.7%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	24.7% ✎	▁▁▁▁▁▁▁▃▁▃▆█ beats 24/246	easy · avg 66%	▇ 0.6%	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	3.9% ✎	▁··▂▃▃▅▇█▇▃▃ beats 18/246	hard · avg 22%	▇ 0.2%	too hard for it · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #233 of 247 · 7.0% of its score · 6 tests

Beats JEV Ettin 150M, JEV FLAN-T5 Large public v2 (342M), Kev 0.8B r15 here, though they rank higher overall. Trails LFM2.5-350M-RLCD, system-one-gemma, Bekko System One v0 17M 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	33.0% ✎	▁▁▃▃▃▃▇▅█▅▃▁ beats 23/246	medium · avg 61%	▇ 2.7%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	49.9% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 14/246	easy · avg 83%	▇ 1.9%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	46.5% ✎	▁·▃▃▂▂▅█▄▂▁▁ beats 2/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	50.0% ✎	▁········▁▇█ beats 14/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	34.8% ✎	▁▃▄█▇▅▁▁▄▄▁▁ beats 17/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	2.4% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 50/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▃▂▂▂▃▃▅▅▆█▂ #246 of 263 · 49% of its score · 14 tests

Beats Amber 0.4B, Dinah-1, Crivo-68M here, though they rank higher overall. Trails CLM-v0.1-8B Qwen3-8B heads, 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: ARC-Easy (accuracy) submitted	57.7% ✎	▁▁▃▁▂▂▂▂▃▆█▅ beats 19/246	very easy · avg 96%	▇▇▇▇▇▇ 15%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	36.6% ✎	▂▃▂▂▂▂▁▃▄▆█▆ beats 14/246	very easy · avg 90%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	34.7% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 21/246	easy · avg 70%	▇▇ 5.9%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	35.0% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 17/246	easy · avg 66%	▇▇ 4.8%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	50.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 16/246	easy · avg 78%	▇ 3.7%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	15.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 22/246	medium · avg 46%	▇ 3.7%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	25.5% ✎	▂▆▅▅▆█▆▃▁··▁ beats 21/246	medium · avg 39%	▇ 1.6%	blunt
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	18.8% ✎	▁··▄█▆▆▆▅▅▃▁ beats 24/246	medium · avg 45%	▇ 1.1%	sharp

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	41.9% ✎	▁▃▂█▅▄▁▁▁▁▁▁ beats 16/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	50.4% ✎	▁███▆▅▃▃▁▁▁▁ beats 15/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	39.5% ✎	██▄▃▃▄▁▁···▁ beats 51/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	4.2% ✎	▁▁▁▁▃▁▁▂▅█▂▁ beats 32/246	hard · avg 22%	▇ 0.4%	too hard for it
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.5% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 33/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	16.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 219/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 5.7% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	8.9600 points ✎	▂▃▂▃▃▃▄▅▅▇█▃ beats 13/247	avg 41.206 points	▇ 3.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	13.6900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 46/247	avg 38.861 points	▇ 2.0%	blunt

$ where to run it

Download model files ↗
Published model files verified. This is the revision recorded by the benchmark. 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/moganai ↗

$ 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		= 23.5

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	49.1%	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]	59.8%	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