Aurelis-2B

+ contribute

Aurelis-2B is an open-weights decision model from Leptos Labs. Its published size is 2.52B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine aurelis-2b; reported model Aurelis-2B. 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.

49.1±1.2#215 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Aurelis-2B, out of 357 with a score.

#	model	score	where	RAM	released
215	Hopper (G) 1.2 Qwen3.5-4B LoRA HopitAI	49±1	model files
216	vLLM-SR d3-nano (2B) vLLM Semantic Router	49±1	local	~8.2GB
217	Aurelis-2B Leptos Labs	49±1	model files
218	zerank-2-reranker (DecisionBench 5eae30d5) zeroentropy	49±2	model files
219	Kev 4B r10 Jared Palmer	49±1	local	~11GB	2026-09-24

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #129 of 250 · 8.1% of its score · 6 tests

Beats Tern-35B-A3B, Cerno 4B v1.1, Trio-Spark DI (9B) here, though they rank higher overall. Trails OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B, razorback16 diffgemma (decision readout) 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	94.3% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 119/246	very easy · avg 92%	▇ 2.7%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	85.2% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 168/236	easy · avg 70%	▇ 2.5%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	90.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 220/246	easy · avg 72%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	72.7% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 178/243	medium · avg 37%	▇ 0.9%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	63.3% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 107/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	78.6% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #127 of 258 · 5.9% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Quyet-1.0-Large, Tern-35B-A3B here, though they rank higher overall. Trails vLLM-SR vela3-fast (Vela 3.0, 0.4B), crystal-0.8b, Kas 4B 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	38.4% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 89/246	medium · avg 38%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	53.2% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 134/246	medium · avg 47%	▇ 2.0%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	59.1% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 43/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	82.1% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 182/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	89.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 120/238	easy · avg 83%	▇ 0.5%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	86.4% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 149/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	64.7% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #142 of 256 · 24% of its score · 9 tests

Beats Solar Decide, JoshuaSP diffgemma (decision readout), PurpleMIST-Flash-1.0 here, though they rank higher overall. Trails Decider 2B, Ryotide Qwen v0.3.1 (decision readout), Sieve 2B v3 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	84.7% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 111/246	very easy · avg 85%	▇▇▇ 6.7%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	72.2% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 87/246	easy · avg 74%	▇▇ 5.4%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	64.1% ✎	▁▂▃▅▅█▂····▁ beats 122/246	medium · avg 60%	▇▇ 5.0%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	37.4% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 81/246	medium · avg 44%	▇ 2.0%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	82.6% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 188/246	easy · avg 71%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	72.9% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 154/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	38.1% ✎	▁··▂▃▃▅▇█▇▃▃ beats 194/246	hard · avg 22%	▇ 0.9%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	75.6% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 132/246	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: FinEntity (macro-F1) submitted	81.5% ✎	▁···▁▁▁▁▃▆█▃ beats 75/246	easy · avg 84%	▇ 0.7%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #62 of 247 · 8.8% 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 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	48.7% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 56/246	medium · avg 61%	▇▇ 3.8%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.9% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 167/246	medium · avg 60%	▇ 1.7%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	94.5% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 187/246	easy · avg 83%	▇ 1.4%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	55.5% ✎	▁········▁▇█ beats 56/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	9.6% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 101/237	hard · avg 21%	▇ 0.6%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	60.8% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 211/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #190 of 263 · 46% of its score · 14 tests

Trails DM-JEPA 1.1, Sieve 2B, Valen-2B 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	39.4% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 80/246	medium · avg 46%	▇▇▇▇ 9.2%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	60.1% ✎	▁▄▄▃▃▃▅▇▅█▇▁ beats 74/246	easy · avg 70%	▇▇▇ 7.4%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	73.8% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 154/246	easy · avg 66%	▇▇▇ 6.4%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	77.5% ✎	▂▂▂▂▂▃▁▃▄▆█▆ beats 64/246	very easy · avg 90%	▇▇ 5.6%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	75.8% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 114/246	easy · avg 78%	▇ 3.3%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	89.9% ✎	▁▁▂▁▂▂▃▂▃▆█▅ beats 64/246	very easy · avg 96%	▇ 3.3%	sharp · maxed out · noisy
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	40.0% ✎	▁··▄█▆▆▆▅▅▃▁ beats 110/246	medium · avg 45%	▇ 3.1%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	41.3% ✎	▂▆▅▅▆█▆▃▁··▁ beats 120/246	medium · avg 39%	▇ 2.7%	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	56.4% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 88/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	39.4% ✎	▁▁▁▁▁▁▁▂▅█▃▁ beats 224/246	hard · avg 22%	▇ 1.1%	typical
Decision Index 0.4.1: CRUXEval (accuracy) submitted	42.6% ✎	██▄▃▃▄▁▁···▁ beats 72/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	85.5% ✎	▁███▆▅▃▃▁▁▁▁ beats 206/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: ChessBench (accuracy) submitted	16.4% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 124/246	hard · avg 16%	▇ 0.5%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	13.2% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 153/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 7.3% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	44.1700 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 120/247	avg 41.206 points	▇▇ 4.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	15.1100 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 56/247	avg 38.861 points	▇ 2.6%	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/Leptos-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		= 49.1

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	78.6%	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]	64.7%	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