whatmodel.sh / decision / vLLM-SR d3-lite (0.8B)

vLLM-SR d3-lite (0.8B)

+ contribute

vLLM-SR d3-lite (0.8B) is an open-weights decision model from vLLM Semantic Router. Its published size is 0.85B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine vllm-sr-d3-lite; reported model vLLM-SR d3-lite (0.8B). 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:lite, manifest 1f9c3e2dd6c2880348e1000ed93088a98b49ee5f298ca65eec6c49d433ffe53e, matching the independent accuracy-run manifest. Native family implementation; published runtime precision label F32. Memory is measured peak GPU increase (4539 MiB, rounded upward to 4.5 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.

42.4±0.9#252 of 355 decision modelsfrom 84 benchmark results across 4 sources

$ how it compares

The decision models ranked either side of vLLM-SR d3-lite (0.8B), out of 357 with a score, then more from vLLM Semantic Router.

#	model	score	where	RAM	released
252	Intelif Qwen3-4B UserMoonlight	43±1	model files
253	Crivo-1B tardellirs	43±1	model files
254	vLLM-SR d3-lite (0.8B) vLLM Semantic Router	42±1	local	~4.5GB
255	OneJev1.5-0.8B OmniJev	42±4	model files		2026-10-13
256	jevhome-ettin-1b (JevBench mini) Jibril Frej	42±2	source code
	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▁▃▁▁▁▂▃▄▆██▆ #188 of 250 · 5.7% of its score · 6 tests

Beats JevK5 v0.3, FlyMy.AI Decision 4B v1.6, RSI-Jev v5.0 VL 3B here, though they rank higher overall. Trails JevK5 Lite, Mola-68M, Mola-150M 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	86.0% ✎	▁▂▁▁▁▂▃▄▅▆█▁ beats 61/246	very easy · avg 92%	▇ 2.5%	sharp · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	56.9% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 64/236	easy · avg 70%	▇ 1.6%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	79.6% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 136/246	easy · avg 72%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	61.4% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 81/246	medium · avg 60%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	11.4% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 70/243	medium · avg 37%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	74.5% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #185 of 258 · 11% of its score · 13 tests

Beats JevK5 9B v0.3.3, JevK5 v0.3, Hopper (G) 1.2 Qwen3.5-4B LoRA here, though they rank higher overall. Trails Mola-68M, Bosun v3.1 1.7B LoRA, Dinah-1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
System One Bench: MASSIVE intent (Arabic)	77.5% ✎	▄·▁·▁▃▃▃█▄▇▇ beats 7/29	easy · avg 76%	▇ 2.7%	at its level
System One Bench: MIRACL pairwise (Arabic)	84.5% ✎	▂···▁··▃▄▂█▇ beats 5/29	easy · avg 84%	▇ 2.5%	at its level
System One Bench: MIRACL rerank (Arabic)	82.5% ✎	▁▂·▁▁·▂·▄▄█▇ beats 7/29	easy · avg 79%	▇ 1.6%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	36.7% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 79/246	medium · avg 38%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	41.3% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 68/246	medium · avg 47%	▇ 1.1%	at its level
System One Bench: MASSIVE scenario (Arabic)	58.0% ✎	▃▁·▄▃▂█▂▁▁·▃ beats 7/29	medium · avg 60%	▇ 0.8%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	81.8% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 160/246	easy · avg 74%	▇ 0.4%	blunt · at its level
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	94.0% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 191/238	easy · avg 83%	▇ 0.3%	sharp · at its level · noisy

5 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	54.9% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 69/245	easy · avg 70%	▇ 0.3%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	90.3% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 186/238	easy · avg 79%	▇ 0.2%	at its level · noisy
System One Bench: AG News (English)	85.5% ✎	▁···▅▁▅▂▆█▂▅ beats 2/29	easy · avg 88%	▇ 0.2%	blunt
System One Bench: Banking77 (English)	91.0% ✎	█▅▆█▅▃▃▃···▂ beats 19/26	very easy · avg 87%	▇ 0.0%	blunt · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	64.3% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #162 of 256 · 22% of its score · 18 tests

Beats PurpleMIST-Flash-1.0, Hopper 12B (trained), Jev-Omni here, though they rank higher overall. Trails DecisionTune 1.0, Decider 2B 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	82.7% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 96/246	very easy · avg 85%	▇▇ 5.4%	sharp
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	66.1% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 62/246	easy · avg 74%	▇ 3.5%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	49.3% ✎	▁▂▃▅▅█▂····▁ beats 63/246	medium · avg 60%	▇ 3.0%	at its level
System One Bench: OSACT4 offensive (Arabic)	80.5% ✎	▁······▁▃█▇▄ beats 4/29	easy · avg 84%	▇ 1.8%	sharp · at its level
System One Bench: BoolQ (English)	81.0% ✎	▁▁▁▃·▁▃▃▇▇█▅ beats 4/29	easy · avg 86%	▇ 1.7%	at its level
System One Bench: SST-2 (English)	86.0% ✎	▁·▃▁▂▂▃▅█·▂▁ beats 1/29	easy · avg 92%	▇ 1.3%	typical
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	32.9% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 68/246	medium · avg 44%	▇ 1.1%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	54.2% ✎	▁▁▁▁▁▁▁▃▂▇▇█ beats 38/246	easy · avg 71%	▇ 0.7%	at its level · noisy

10 more tests

test	result	vs the others in its run	difficulty	counts	why
System One Bench: SST-5 (English)	50.5% ✎	▃·▁▁▃·▇▄▄▄█▅ beats 6/29	medium · avg 51%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: VAST (macro-F1) submitted	55.4% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 95/246	medium · avg 62%	▇ 0.6%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	88.1% ✎	▁···▁▁▁▁▃▆█▃ beats 126/246	easy · avg 84%	▇ 0.5%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	29.7% ✎	▁▁▁▁▁▁▁▃▁▃▆█ beats 31/246	easy · avg 66%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: ACOS (per-review F1) submitted	6.5% ✎	▁··▂▃▃▅▇█▇▃▃ beats 34/246	hard · avg 22%	▇ 0.4%	noisy
System One Bench: XNLI French (French)	81.3% ✎	▂▅·▁▁▅▅█▃▁·▃ beats 15/29	medium · avg 76%	▇ 0.4%	blunt · at its level
System One Bench: XNLI Arabic (Arabic)	72.7% ✎	▄▁▃▁▄▇█▅▃▁·▃ beats 13/29	medium · avg 68%	▇ 0.4%	at its level
System One Bench: Tweet sentiment (Arabic)	67.0% ✎	▁······▁▁▄█▄ beats 14/29	medium · avg 62%	▇ 0.2%	blunt · at its level
System One Bench: XNLI English (English)	90.7% ✎	▃·▁·▃▇█▄█▃▃▁ beats 20/29	easy · avg 85%	▇ 0.1%	blunt · at its level · noisy
System One Bench: DAIR Emotion (English)	57.0% ✎	██▃·····▁··▁ beats 14/29	medium · avg 59%	▇ 0.0%	blunt · at its level

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #179 of 247 · 5.2% of its score · 6 tests

Beats Sieve 9B, Kev 9B v2, vLLM-SR d3-nano (2B) here, though they rank higher overall. Trails Bekko System One v0 68M, Crivo-17M, Crivo-32M v2 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	61.6% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 110/246	medium · avg 61%	▇ 2.3%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	71.3% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 68/246	easy · avg 83%	▇ 1.0%	sharp · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	57.3% ✎	▁·▁▃▂▃▅█▄▂▁▁ beats 69/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	58.7% ✎	▁········▁▇█ beats 89/246	medium · avg 60%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	1.6% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 37/237	hard · avg 21%	▇ 0.2%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	38.0% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 38/246	medium · avg 47%	▇ 0.2%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #197 of 263 · 34% of its score · 19 tests

Beats OneJev1.6-0.8B, GLiClass v4 edge (0.4B), Crivo-1B here, though they rank higher overall. Trails laya (DecisionBench 1c5edc17), DM-JEPA 1.1, 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	77.6% ✎	▂▂▂▂▂▃▁▃▄▆█▆ beats 65/246	very easy · avg 90%	▇▇ 5.1%	sharp
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	32.5% ✎	▄▄▃▃▃▄▅▇██▅▁ beats 68/246	medium · avg 46%	▇▇ 4.9%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	56.2% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 68/246	easy · avg 70%	▇▇ 4.8%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	46.6% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 57/246	easy · avg 66%	▇▇ 3.9%	at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	90.4% ✎	▁▁▂▁▂▂▃▂▃▆█▅ beats 66/246	very easy · avg 96%	▇ 3.6%	sharp · noisy
Decision Index 0.4.1: WinoGrande (accuracy) submitted	70.9% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 92/246	easy · avg 78%	▇ 2.2%	at its level
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	41.6% ✎	▁··▄█▆▆▆▅▅▃▁ beats 117/246	medium · avg 45%	▇ 1.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	33.2% ✎	▂▆▅▅▆█▆▃▁··▁ beats 74/246	medium · avg 39%	▇ 1.5%	blunt · at its level

11 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · PubMedQA	60.4% ✎	▃▂▃▃·▃▃▃▆█▆▂ beats 7/25	easy · avg 69%	▇ 1.3%	at its level
Ollaya · BoolQ	81.3% ✎	▁··▃▃▁▄▃▃█▇▄ beats 9/25	easy · avg 84%	▇ 1.1%	typical
Decision Index 0.4.1: MuSR (accuracy) submitted	57.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 102/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	33.7% ✎	██▄▃▃▄▁▁···▁ beats 17/246	medium · avg 58%	▇ 0.6%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	61.1% ✎	▁███▆▅▃▃▁▁▁▁ beats 68/246	easy · avg 71%	▇ 0.6%	at its level
Ollaya · SQuAD 2 answerability	72.9% ✎	▁▁▃▁▇█▃▃▄▃·▁ beats 6/25	easy · avg 80%	▇ 0.6%	blunt
Ollaya · VitaminC verification	78.0% ✎	▁···▃·▄█▃··▁ beats 16/25	easy · avg 78%	▇ 0.5%	blunt · at its level
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	19.6% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 71/246	hard · avg 22%	▇ 0.5%	typical
Ollaya · MultiNLI	88.0% ✎	▂··▄██▂▆▆█▆▂ beats 15/25	very easy · avg 87%	▇ 0.3%	blunt
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.3% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 28/246	hard · avg 16%	▇ 0.3%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	14.4% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 183/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #75 of 79 · 6.2% of its score · 12 tests

Trails LiquidAI d1-omni-600M, Valen-0.8B, InternLM Intern-Decision Qwen3.5-2B 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	50.6700 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 7/61	avg 63.423 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	7.2500 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 3/61	avg 22.797 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	54.5000 points ✎	▁·▁▁▁▃·▂▁▃▅█ beats 8/61	avg 66.987 points	▇ 0.7%	blunt
Decision Index Vision 0.4: private same skills (points)	36.3300 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 4/61	avg 48.067 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	13.1100 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 5/61	avg 28.443 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	36.1800 points ✎	▁·▃▂▁▃▃▅▅▃▂█ beats 2/61	avg 53.651 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	53.1300 points ✎	▂▁▁▁▃▃▁▅▅▆██ beats 8/61	avg 62.137 points	▇ 0.5%	blunt
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	73.2200 points ✎	▁·▁▃▁▁▃▁▂▂▅█ beats 5/61	avg 83.859 points	▇ 0.4%	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	9.4000 points ✎	▃▄▇▆█▄▄▇▂··▁ beats 2/61	avg 19.676 points	▇ 0.4%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	38.1400 points ✎	▁···▁▂▃▂█▄▂▃ beats 10/61	avg 44.994 points	▇ 0.4%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	65.0300 points ✎	▁▁▁▁▂▃▁▁▄█▃▃ beats 11/61	avg 67.662 points	▇ 0.3%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	76.2900 points ✎	▁··▁▃▁▁▁▂▄█▁ beats 4/61	avg 85.184 points	▇ 0.2%	blunt

workflows▁▁▁▂▁▂▃▆█▄▁▁ #81 of 114 · 11% of its score · 10 tests

Trails InternLM Intern-Decision Qwen3.5-2B, vLLM-SR Decision 2.0 Sol 2B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Ollaya · Typed decisions test	52.6% ✎	▄·▂▆▄▄▂·▄█▆▆ beats 8/22	medium · avg 64%	▇ 2.1%	at its level
System One Bench: Typed decisions (English)	52.6% ✎	▁▁·▃▁▁▅▄▇██▁ beats 2/29	medium · avg 63%	▇ 1.9%	blunt · at its level
Ollaya · PAWS paraphrase	84.4% ✎	▂▂▂▂·▃█▆·▂·▁ beats 20/25	easy · avg 81%	▇ 1.4%	at its level
Ollaya · MASSIVE German intent	81.7% ✎	▁····▁·▂▃▆█▃ beats 11/23	easy · avg 84%	▇ 1.4%	sharp
Ollaya · Aegis 2 safety	59.2% ✎	▂·▁▃▂·▃▃▂█▃▁ beats 3/25	easy · avg 77%	▇ 1.1%	at its level
Ollaya · SummEval relevance	50.4% ✎	▁··▁▂▁▅··▃██ beats 21/25	medium · avg 41%	▇ 0.9%	at its level
Ollaya · SummEval consistency	9.0% ✎	▁·▁▃··▁▁▁▁▄█ beats 2/25	easy · avg 75%	▇ 0.7%	sharp · at its level · noisy
Ollaya · MASSIVE English intent	84.6% ✎	▁·······▂▃█▃ beats 12/23	very easy · avg 86%	▇ 0.7%	noisy

2 more tests

test	result	vs the others in its run	difficulty	counts	why
Ollaya · HelpSteer 2 scoring	32.1% ✎	▁▁··▁·▁▃▇█▅▄ beats 4/23	medium · avg 38%	▇ 0.4%	blunt · at its level
Ollaya · Civil Comments	89.3% ✎	▂▂▂·▂▅▅▆▃▅·█ beats 16/23	very easy · avg 86%	▇ 0.1%	blunt · noisy

other tests2 not in a task · 4.2% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	34.1600 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 74/247	avg 41.206 points	▇ 2.7%	blunt
Decision Index 0.4.1: private new domains (equated points)	14.1700 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 52/247	avg 38.861 points	▇ 1.5%	blunt

$ where to run it

Other ways to run it

Run it as published · needs 4.5 GB, NVIDIA only · from github.com/ollaya-dev
ollaya run d3:lite --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 65%, 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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 65%	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	▇▇ 6%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 42.4

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	74.5%	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]	64.3%	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