whatmodel.sh / decision / vLLM-SR d3-nano (2B)

vLLM-SR d3-nano (2B)

+ contribute

vLLM-SR d3-nano (2B) is an open-weights decision model from vLLM Semantic Router. Its published size is 2.21B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine vllm-sr-d3-nano; reported model vLLM-SR d3-nano (2B). Type: full fine-tune; technique: autoregressive. No 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. Reviewed Ollaya local route added 2026-10-31: d3:nano, manifest 137bd4f1edd15d843102431d9b4ed066e581549fc3a5e61f72e6d09a28519ecf, matching the independent accuracy-run manifest. Native family implementation; published runtime precision label F32. Memory is measured peak GPU increase (8363 MiB, rounded upward to 8.2 GiB) on RTX 5090 during the short five-question triage workload, not download size or a maximum-context guarantee. Runtime installation is required; no fresh execution performed here. Historical benchmark adapter and input protocol still vary by result.

Model information sources

· Weights licence ↗ · Parameter count ↗

Publisher parameter count; includes the served backbone, not just adapter size.

49.2±0.9#214 of 355 decision modelsfrom 84 benchmark results across 4 sources

$ how it compares

The decision models ranked either side of vLLM-SR d3-nano (2B), out of 357 with a score, then more from vLLM Semantic Router.

#	model	score	where	RAM	released
214	Nari Decision 4B v3.2 blackmallangcow	49±1	model files		2026-10-18
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
	more from vLLM Semantic Router
8	vLLM-SR d3-ultra (Decision 3.0, 27B) vLLM Semantic Router	72±1	model files
9	vLLM-SR d3-turbo v1.1 (27B) vLLM Semantic Router	72±1	model files
25	vLLM-SR d3 (27B) vLLM Semantic Router	69±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #156 of 250 · 5.2% of its score · 6 tests

Beats Trio-Spark DI (9B), Decider 35B-A3B, LiquidAI d1-3B here, though they rank higher overall. Trails JevK5 Lite, Gevva E2B, 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: BFCL (case exact accuracy) submitted	92.2% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 92/246	very easy · avg 92%	▇ 1.7%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	56.3% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 62/236	easy · avg 70%	▇ 1.6%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	82.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 158/246	easy · avg 72%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	12.5% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 74/243	medium · avg 37%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	61.2% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 79/246	medium · avg 60%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.0% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #161 of 258 · 12% of its score · 13 tests

Beats Solar Decide, decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout), JevK5 9B v0.3.3 here, though they rank higher overall. Trails DecisionTune 1.0, jiwo 0.8B v2, Amber 0.4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
System One Bench: MASSIVE intent (Arabic)	81.0% ✎	▄·▁·▁▃▃▃█▄▇▇ beats 9/29	easy · avg 76%	▇ 2.6%	at its level
System One Bench: MIRACL pairwise (Arabic)	86.5% ✎	▂···▁··▃▄▂█▇ beats 8/29	easy · avg 84%	▇ 2.6%	at its level
System One Bench: MIRACL rerank (Arabic)	77.5% ✎	▁▂·▁▁·▃·▄▄█▇ beats 5/29	easy · avg 79%	▇ 1.6%	typical
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	39.0% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 94/246	medium · avg 38%	▇ 1.3%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	47.1% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 92/246	medium · avg 47%	▇ 1.3%	at its level
System One Bench: MASSIVE scenario (Arabic)	61.5% ✎	▃▁·▄▃▂█▂▁▁·▃ beats 9/29	medium · avg 60%	▇ 0.9%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	79.9% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 143/246	easy · avg 74%	▇ 0.4%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	67.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 116/245	easy · avg 70%	▇ 0.3%	at its level · noisy

5 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	95.1% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 206/238	easy · avg 83%	▇ 0.3%	sharp · noisy
System One Bench: AG News (English)	88.0% ✎	▁···▅▁▅▂▆█▂▅ beats 8/29	easy · avg 88%	▇ 0.2%	blunt
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	91.3% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 204/238	easy · avg 79%	▇ 0.2%	noisy
System One Bench: Banking77 (English)	93.0% ✎	█▅▆█▅▃▃▃···▂ beats 20/26	very easy · avg 87%	▇ 0.0%	blunt · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	63.2% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #121 of 256 · 22% of its score · 18 tests

Beats garum (Gemma 4 31B), Shisa DE-2.1 (repeat), garas (Gemma 4 31B) 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	91.0% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 133/246	very easy · avg 85%	▇▇ 4.3%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	71.6% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 82/246	easy · avg 74%	▇ 3.5%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	56.0% ✎	▁▂▃▅▅█▂····▁ beats 86/246	medium · avg 60%	▇ 3.2%	at its level
System One Bench: OSACT4 offensive (Arabic)	79.0% ✎	▁······▁▃█▇▄ beats 3/29	easy · avg 84%	▇ 1.8%	sharp · at its level
System One Bench: BoolQ (English)	88.0% ✎	▁▁▁▃·▁▃▃▇▇█▅ beats 9/29	easy · avg 86%	▇ 1.7%	at its level
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	40.1% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 92/246	medium · avg 44%	▇ 1.3%	at its level
System One Bench: SST-2 (English)	89.5% ✎	▁·▃▃▂▂▃▅█·▂▁ beats 4/29	easy · avg 92%	▇ 1.2%	typical
System One Bench: SST-5 (English)	55.5% ✎	▃·▁▁▃·▇▄▄▄█▅ beats 14/29	medium · avg 51%	▇ 0.7%	blunt · at its level

10 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	68.8% ✎	▁▁▁▁▁▁▁▂▃▇▇█ beats 69/246	easy · avg 71%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	57.0% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 100/246	medium · avg 62%	▇ 0.6%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	13.0% ✎	▁··▂▃▃▅▇█▇▃▃ beats 73/246	hard · avg 22%	▇ 0.6%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	29.5% ✎	▁▁▁▁▁▁▁▃▁▃▆█ beats 29/246	easy · avg 66%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: FinEntity (macro-F1) submitted	87.6% ✎	▁···▁▁▁▁▃▆█▃ beats 118/246	easy · avg 84%	▇ 0.5%	noisy
System One Bench: XNLI Arabic (Arabic)	82.0% ✎	▄▁▃▁▄▇█▅▃▁·▃ beats 26/29	medium · avg 68%	▇ 0.4%	at its level
System One Bench: XNLI French (French)	86.0% ✎	▂▅·▁▁▅▅█▃▁·▃ beats 24/29	medium · avg 76%	▇ 0.4%	blunt · at its level
System One Bench: Tweet sentiment (Arabic)	71.0% ✎	▁······▁▁▄█▄ beats 20/29	medium · avg 62%	▇ 0.3%	blunt · at its level
System One Bench: XNLI English (English)	87.3% ✎	▃·▁·▃▇█▄█▃▃▁ beats 13/29	easy · avg 85%	▇ 0.1%	blunt · noisy
System One Bench: DAIR Emotion (English)	59.5% ✎	██▃·····▁··▁ beats 21/29	medium · avg 59%	▇ 0.0%	blunt · at its level

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #202 of 247 · 5.6% of its score · 6 tests

Trails LFM2.5-350M-RLCD, system-one-gemma, 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: New Yorker (accuracy) submitted	70.6% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 157/246	medium · avg 61%	▇ 2.4%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	60.5% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 106/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	56.6% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 45/246	easy · avg 83%	▇ 0.9%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	61.1% ✎	▁········▁▇█ beats 114/246	medium · avg 60%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	10.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 105/237	hard · avg 21%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	36.7% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 29/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #172 of 263 · 33% of its score · 19 tests

Beats Solomon v1.1, Standard One 3B SH (v4), baselabs joey-1 (2B) here, though they rank higher overall. Trails openvons Qwen3-4B (decision readout), Jevstral 8B, Jobe Qwen3.5-4B (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	43.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 91/246	medium · avg 46%	▇▇ 5.9%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	67.1% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 85/246	easy · avg 70%	▇▇ 4.7%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	54.4% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 72/246	easy · avg 66%	▇▇ 4.1%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	88.8% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 88/246	very easy · avg 90%	▇ 3.6%	sharp
Decision Index 0.4.1: WinoGrande (accuracy) submitted	79.9% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 125/246	easy · avg 78%	▇ 2.1%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	96.4% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 95/246	very easy · avg 96%	▇ 2.1%	sharp · maxed out · noisy
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	51.8% ✎	▁··▄█▆▆▆▅▅▃▁ beats 140/246	medium · avg 45%	▇ 2.0%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	32.1% ✎	▂▆▅▅▆█▆▃▁··▁ beats 68/246	medium · avg 39%	▇ 1.7%	blunt · at its level

11 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · PubMedQA	67.6% ✎	▃▂▃▃·▂▃▃▆█▆▂ beats 11/25	easy · avg 69%	▇ 1.4%	at its level
Ollaya · BoolQ	87.7% ✎	▁··▃▃▁▄▁▃█▇▄ beats 21/25	easy · avg 84%	▇ 1.1%	typical
Decision Index 0.4.1: MuSR (accuracy) submitted	59.6% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 129/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	29.8% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 141/246	hard · avg 22%	▇ 0.7%	typical
Decision Index 0.4.1: CRUXEval (accuracy) submitted	41.8% ✎	██▄▃▃▄▁▁···▁ beats 68/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	60.3% ✎	▁███▆▅▃▃▁▁▁▁ beats 66/246	easy · avg 71%	▇ 0.6%	at its level
Ollaya · SQuAD 2 answerability	73.9% ✎	▁▁▃▁▇█▃▃▄▃·▁ beats 7/25	easy · avg 80%	▇ 0.6%	blunt
Ollaya · VitaminC verification	80.5% ✎	▁···▃·▄█▃··▁ beats 22/25	easy · avg 78%	▇ 0.5%	blunt
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.7% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 41/246	hard · avg 16%	▇ 0.3%	blunt
Ollaya · MultiNLI	88.6% ✎	▂··▄██▂▆▆█▆▂ beats 16/25	very easy · avg 87%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	14.0% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 172/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #62 of 79 · 6.9% of its score · 12 tests

Beats djev diffgemma (decision readout) here, though they rank higher overall. Trails TokenRhythm NeoHorse-Jev-4B, RSI-Jev v5.0 VL 3B, Valen-4B 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	63.6900 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 16/61	avg 63.423 points	▇ 0.9%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	17.7900 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 14/61	avg 22.797 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	69.0000 points ✎	▁·▁▁▁▁·▂▃▃▅█ beats 16/61	avg 66.987 points	▇ 0.8%	blunt
Decision Index Vision 0.4: private same skills (points)	50.1900 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 18/61	avg 48.067 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	23.6600 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 15/61	avg 28.443 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	53.1100 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 16/61	avg 53.651 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	65.1600 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 18/61	avg 62.137 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	83.6100 points ✎	▁·▁▂▁▁▃▁▂▂▅█ beats 18/61	avg 83.859 points	▇ 0.5%	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	15.5400 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 11/61	avg 19.676 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	50.3800 points ✎	▁···▁▂▂▃█▄▂▃ beats 18/61	avg 44.994 points	▇ 0.4%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	71.9100 points ✎	▁▁▁▁▂▁▁▁▄█▃▃ beats 20/61	avg 67.662 points	▇ 0.3%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	83.9700 points ✎	▁··▁▁▁▁▃▂▄█▁ beats 8/61	avg 85.184 points	▇ 0.2%	blunt

workflows▁▁▁▂▁▂▂▆█▄▁▁ #73 of 114 · 11% of its score · 10 tests

Beats ZTC-Judge-9B (DecisionBench 05d154a5), djev-spark (DecisionBench 1444f3e9) here, though they rank higher overall. Trails Solar Decide Flash, InternLM Intern-Decision Qwen3.5-4B, StartLux-Decision v1.1 0.8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Typed decisions test	62.5% ✎	▄·▂▆▄▄▂·▄█▆▆ beats 11/22	medium · avg 64%	▇ 2.2%	at its level
System One Bench: Typed decisions (English)	62.6% ✎	▁▁·▁▁▁▅▄▇██▁ beats 6/29	medium · avg 63%	▇ 2.0%	blunt · at its level
Ollaya · PAWS paraphrase	85.2% ✎	▂▂▂▂·▃█▆·▂·▁ beats 21/25	easy · avg 81%	▇ 1.4%	typical
Ollaya · MASSIVE German intent	82.3% ✎	▁····▁·▂▃▆█▃ beats 12/23	easy · avg 84%	▇ 1.2%	sharp
Ollaya · SummEval relevance	47.9% ✎	▁··▁▂▁▅··▃██ beats 18/25	medium · avg 41%	▇ 1.1%	at its level
Ollaya · Aegis 2 safety	70.4% ✎	▂·▁▁▂·▃▃▂█▃▁ beats 8/25	easy · avg 77%	▇ 1.1%	typical
Ollaya · SummEval consistency	77.8% ✎	▁·▁▁··▁▁▁▁▄█ beats 10/25	easy · avg 75%	▇ 0.7%	sharp · at its level · noisy
Ollaya · MASSIVE English intent	84.3% ✎	▁·······▂▃█▃ beats 11/23	very easy · avg 86%	▇ 0.6%	noisy

2 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · HelpSteer 2 scoring	43.4% ✎	▁▁··▁·▁▃▇█▅▄ beats 21/23	medium · avg 38%	▇ 0.4%	blunt · at its level
Ollaya · Civil Comments	93.0% ✎	▂▂▂·▂▅▅▆▃▅·█ beats 21/23	very easy · avg 86%	▇ 0.1%	blunt · noisy

other tests2 not in a task · 4.7% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	41.9100 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 110/247	avg 41.206 points	▇ 3.0%	blunt
Decision Index 0.4.1: private new domains (equated points)	22.8900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 79/247	avg 38.861 points	▇ 1.7%	blunt

$ where to run it

Other ways to run it

Run it as published · needs 8.2 GB, NVIDIA only · from github.com/ollaya-dev
ollaya run d3:nano --preset triage "The customer requests a refund."

Download model files ↗
Published model files verified. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. A matching Ollaya runtime manifest and published short-workload GPU memory measurement were reviewed separately; see local variants and identity_note. The command was not executed in this review. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/vllm-sr ↗

$ how the score was worked out · Decision Index 0.4.1 64%, System One Bench (Ali Alhashi… 16%, Ollaya · original runs 13% and 1 more

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 64%	CC BY 4.0
System One Bench (Ali Alhashimi)	16	▇▇▇▇▇ 16%	CC-BY-4.0
Ollaya · original runs	14	▇▇▇▇ 13%	Apache-2.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇ 7%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 49.2

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.0%	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]	63.2%	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