whatmodel.sh / decision / Blink v0.3 26B-A4B (NVFP4)

Blink v0.3 26B-A4B (NVFP4)

+ contribute

Blink v0.3 26B-A4B (NVFP4) is an open-weights decision model from Pixilab.ai. Its published size is 25.8B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine blink-v0.3-26b-a4b-nvfp4; reported model Blink v0.3 26B-A4B (NVFP4). 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.

61.5±1.3#92 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Blink v0.3 26B-A4B (NVFP4), out of 357 with a score.

#	model	score	where	RAM	released
90	Perplexity Decider Flash v1.2 (4B) Perplexity	62±1	local	~10GB
91	Wald-26B-A4B ORG2 AI	62±1	model files
92	Blink v0.3 26B-A4B (NVFP4) Pixilab.ai	62±1	model files
93	imajev-4b (DecisionBench 712891d1) mohit67890	62±2	model files
94	GPT-6 Luna Decisions OpenAI	62±1	api price unknown		2026-10-06

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #102 of 250 · 6.6% of its score · 6 tests

Beats Jev 1.13, Xor 26B-A4B v1.2, Senova-4B v2 here, though they rank higher overall. Trails OneJev1.6-0.8B, TokenRhythm NeoHorse-Jev-4B, mmastrac 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: API-Bank (accuracy) submitted	82.3% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 128/236	easy · avg 70%	▇ 2.0%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	96.0% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 148/246	very easy · avg 92%	▇ 1.3%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	48.9% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 131/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	66.1% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 165/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy) submitted	67.5% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 87/246	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▁▁▁·▁▁▁▁▃▃█▅ #97 of 258 · 7.2% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Decider 31B (NVFP4), Quyet-1.0-Large here, though they rank higher overall. Trails Jev-Style 2B v4, Sieve 2B v3, StartLux-Decision v1.1 0.8B 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	47.1% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 185/246	medium · avg 38%	▇ 2.8%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	55.2% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 154/246	medium · avg 47%	▇ 2.5%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	79.3% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 141/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	79.5% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 171/245	easy · avg 70%	▇ 0.6%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	88.6% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 106/238	easy · avg 83%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	83.5% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 123/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	67.9% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #116 of 256 · 22% of its score · 9 tests

Beats garum (Gemma 4 31B), Shisa DE-2.1 (repeat) here, though they rank higher overall. Trails Decider 4B, jiwo 4B v2, Sieve 4B 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	72.0% ✎	▁▂▃▅▅█▂····▁ beats 173/246	medium · avg 60%	▇▇ 5.5%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	78.8% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 143/246	easy · avg 74%	▇▇ 5.3%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	91.5% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 136/246	very easy · avg 85%	▇▇ 3.8%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	68.1% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 218/246	medium · avg 44%	▇ 2.6%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	28.2% ✎	▁··▂▃▃▅▇█▇▃▃ beats 158/246	hard · avg 22%	▇ 1.5%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	77.1% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 185/246	medium · avg 62%	▇ 1.1%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	77.0% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 135/246	easy · avg 71%	▇ 1.0%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	80.3% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 178/246	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	90.6% ✎	▁···▁▁▁▁▃▆█▃ beats 156/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #112 of 247 · 10% of its score · 6 tests

Beats Bobcat 1.3 (31B), Nace.AI Drex v2.0 (35B-A3B), decisio 0.6.0 (Gemma 4 31B) (decision readout) here, though they rank higher overall. Trails vLLM-SR vela3-fast-vision (Vela 3.0, 0.25B), Crivo-400M, Amber 0.4B 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	73.7% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 177/246	medium · avg 61%	▇▇ 4.1%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.4% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 159/246	medium · avg 60%	▇ 2.1%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	62.8% ✎	▁········▁▇█ beats 140/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	65.8% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 190/237	hard · avg 21%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	89.8% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 135/246	easy · avg 83%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	45.4% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 139/246	medium · avg 47%	▇ 0.4%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #78 of 263 · 44% of its score · 14 tests

Beats StartLux-Decision v1.1 9B, Sieve 27B v2, StartLux-Decision v1.1 4B here, though they rank higher overall. Trails Solar Decide, Clef-flash, Decider chat · Qwen3.6-27B (decision readout) 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	66.4% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 187/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	83.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 166/246	easy · avg 70%	▇▇▇ 6.4%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	81.4% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 200/246	easy · avg 66%	▇▇ 6.2%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	75.4% ✎	▁··▄█▆▆▆▅▅▃▁ beats 206/246	medium · avg 45%	▇ 3.7%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	45.4% ✎	▂▆▅▅▆█▆▃▁··▁ beats 156/246	medium · avg 39%	▇ 3.7%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	84.9% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 158/246	easy · avg 78%	▇ 2.9%	typical
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	96.9% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 192/246	very easy · avg 90%	▇ 2.6%	sharp · maxed out
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	34.1% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 194/246	hard · avg 22%	▇ 1.8%	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	66.4% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 192/246	medium · avg 60%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	73.9% ✎	██▄▃▃▄▁▁···▁ beats 181/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.8% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 167/246	very easy · avg 96%	▇ 1.1%	sharp · maxed out · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	71.8% ✎	▁███▆▅▃▃▁▁▁▁ beats 136/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	17.8% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 147/246	hard · avg 16%	▇ 0.8%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	11.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 101/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 9.5% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	56.8100 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 186/247	avg 41.206 points	▇▇ 6.1%	blunt
Decision Index 0.4.1: private new domains (equated points)	54.5700 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 171/247	avg 38.861 points	▇ 3.4%	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/PixilabAI ↗

$ 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		= 61.5

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]	67.9%	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