Valen-2B

+ contribute

Valen-2B is an open-weights decision model from Valen. Its published size is 2.21B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine valen-2b-r2; reported model Valen-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.

39.4±1.0#266 of 355 decision modelsfrom 54 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of Valen-2B, out of 357 with a score, then more from Valen.

#	model	score	where	released
266	jdi-ptr14-0.8b AnamK	40±1	model files
267	Saina Helm 2.0 v2 Saina	39±1	model files
268	Valen-2B Valen	39±1	model files
269	Saina Helm 2 Omni (0.8B) Saina	39±1	model files
270	EXAONE-4.0-1.2B-JEV v0.3 carrtesy	39±1	model files	2026-10-04
	more from Valen
227	Valen-4B Valen	48±1	model files
288	Valen-0.8B Valen	34±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #191 of 250 · 8.3% of its score · 6 tests

Beats JevK5 v0.3, FlyMy.AI Decision 4B v1.6, openvons Qwen3-4B (decision readout) here, though they rank higher overall. Trails JevK5 Lite, Mola-68M, Dinah-1 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	84.8% ✎	▁▂▁▁▁▂▃▄▅▆█▁ beats 58/246	very easy · avg 92%	▇▇ 4.0%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	52.8% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 56/236	easy · avg 70%	▇ 2.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	47.5% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 38/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	58.0% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 55/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	4.5% ✎	█▁▃▃▄▄▆▄▁▂▁▃ beats 58/243	medium · avg 37%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	78.2% ✎	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▁▁▁·▁▁▃▁▃▃█▅ #221 of 258 · 4.7% of its score · 7 tests

Beats Intelif Qwen3-4B, mini-jev Qwen3-4B (decision readout), open-jev (pngwn) here, though they rank higher overall. Trails Bosun v3.1 0.6B LoRA, Crivo-32M v2, Jev-Style 0.8B v3 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	34.0% ✎	▁▁▁▁▁▁▁▂▃▄▇█ beats 67/246	medium · avg 38%	▇ 1.5%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	31.1% ✎	▁▁▁▁▁▁▂▃▃▃█▅ beats 37/246	medium · avg 47%	▇ 1.5%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	56.2% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 27/246	easy · avg 74%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	39.7% ✎	▁▁▁▁▁▁▃▂▃▆█▄ beats 20/238	easy · avg 83%	▇ 0.5%	sharp · at its level · noisy
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	50.5% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 38/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	57.4% ✎	▁·▁▁▁▁▁▁▃█▇█ beats 19/238	easy · avg 79%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	54.6% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #215 of 256 · 22% of its score · 9 tests

Trails LiquidAI d1-omni-600M, DecisionTune 1.0, vera-spark 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	57.6% ✎	▂▄▂▃▄▇▃▇█▅▃▁ beats 41/246	very easy · avg 85%	▇▇▇ 8.2%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	70.0% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 79/246	easy · avg 74%	▇▇ 4.9%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	48.3% ✎	▁▂▃▅▅█▂····▁ beats 59/246	medium · avg 60%	▇▇ 4.0%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	26.2% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 41/246	medium · avg 44%	▇ 1.4%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	78.4% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 147/246	easy · avg 71%	▇ 0.9%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	65.9% ✎	▁···▁▁▁▁▃▆█▃ beats 33/246	easy · avg 84%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	50.5% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 77/246	medium · avg 62%	▇ 0.8%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	50.1% ✎	▁▁▁▁▁▁▁▁▃▃▆█ beats 45/246	easy · avg 66%	▇ 0.7%	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	17.9% ✎	▁··▂▃▃▅▇█▇▃▃ beats 97/246	hard · avg 22%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #183 of 247 · 7.1% of its score · 6 tests

Beats Sieve 9B, Kev 9B v2, vLLM-SR d3-nano (2B) here, though they rank higher overall. Trails Qwen-2.5-1B-RLCD (decision readout), Bekko System One v0 68M, Crivo-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	43.8% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 44/246	medium · avg 61%	▇ 3.1%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	67.3% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 64/246	easy · avg 83%	▇ 1.5%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	55.3% ✎	▁·▁▃▂▃▅█▄▂▁▁ beats 60/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	59.1% ✎	▁········▁▇█ beats 93/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	0.3% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 3/237	hard · avg 21%	▇ 0.2%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	41.3% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 87/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #188 of 263 · 43% of its score · 14 tests

Beats Aurelis-2B, StartLux-Decision v1.1 0.8B, Sieve 2B v3 here, though they rank higher overall. Trails Sieve 2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	82.2% ✎	▂▂▂▂▂▂▃▃▄▆█▆ beats 72/246	very easy · avg 90%	▇▇▇ 8.1%	sharp
Decision Index 0.4.1: MMLU (accuracy) submitted	57.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 72/246	easy · avg 70%	▇▇▇ 6.6%	sharp · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	93.6% ✎	▁▁▂▁▂▂▂▃▃▆█▅ beats 76/246	very easy · avg 96%	▇▇▇ 6.4%	sharp · noisy
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	37.2% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 77/246	medium · avg 46%	▇▇ 6.2%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	51.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 66/246	easy · avg 66%	▇▇ 5.4%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	57.2% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 36/246	easy · avg 78%	▇ 3.2%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	28.7% ✎	▁··▄█▆▆▆▅▅▃▁ beats 72/246	medium · avg 45%	▇ 2.0%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	33.7% ✎	▂▆▅▅▆█▆▃▁··▁ beats 78/246	medium · avg 39%	▇ 1.9%	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	59.3% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 126/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	57.9% ✎	▁███▆▅▃▃▁▁▁▁ beats 58/246	easy · avg 71%	▇ 0.8%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	36.0% ✎	██▄▃▃▄▁▁···▁ beats 31/246	medium · avg 58%	▇ 0.8%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	10.5% ✎	▁▁▁▁▁▁▃▂▅█▂▁ beats 45/246	hard · avg 22%	▇ 0.6%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	10.0% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 59/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 96/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #65 of 79 · 8.4% of its score · 12 tests

Beats djev diffgemma (decision readout), StartLux-Decision v1.1 0.8B, mmastrac diffgemma (decision readout) here, though they rank higher overall. Trails LiquidAI d1-omni-600M here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · Mind2Web (chance-corrected points) submitted	50.3900 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 6/61	avg 63.423 points	▇ 1.1%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	15.3400 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 10/61	avg 22.797 points	▇ 1.0%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	63.7500 points ✎	▁·▁▁▁▁·▃▁▃▅█ beats 13/61	avg 66.987 points	▇ 0.9%	blunt
Decision Index Vision 0.4: private same skills (points)	42.6900 points ✎	▁▁▃▃▃▂▄▆▃▃▅█ beats 12/61	avg 48.067 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	14.5900 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 7/61	avg 28.443 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	58.6600 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 26/61	avg 53.651 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	63.6600 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 16/61	avg 62.137 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	83.6100 points ✎	▁·▁▂▁▁▃▁▂▂▅█ beats 17/61	avg 83.859 points	▇ 0.6%	blunt

4 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted	19.6900 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 24/61	avg 19.676 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	45.8700 points ✎	▁···▁▂▂▃█▄▂▃ beats 14/61	avg 44.994 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	68.7500 points ✎	▁▁▁▁▂▁▁▃▄█▃▃ beats 16/61	avg 67.662 points	▇ 0.4%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	86.6400 points ✎	▁··▁▁▁▁▁▃▄█▁ beats 12/61	avg 85.184 points	▇ 0.3%	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)	23.5100 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 47/247	avg 41.206 points	▇ 3.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	20.2200 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 75/247	avg 38.861 points	▇ 2.0%	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/Valen-Team ↗

$ how the score was worked out · Decision Index 0.4.1 91%, Decision Index Vision 0.4 8%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 91%	CC BY 4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇▇ 8%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 39.4

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	78.2%	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]	54.6%	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