whatmodel.sh / decision / Jebadiah 9B v2.1 (T1e)

Jebadiah 9B v2.1 (T1e)

+ contribute

Jebadiah 9B v2.1 (T1e) is an open-weights decision model from frontier-infra, released October 2026. Its published size is 9.653B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index 0.4.1 text-board engine jebadiah-9b-v2.1-t1e. Produces probabilities over supplied choices, not conversational text. Only public per-benchmark results are used; no Full index, private scores or latency is treated as an ability measurement. Model and runtime documentation reviewed 2026-10-31; no fresh hardware execution. T1e uses repeated payloads, forward/reverse choice scoring with threshold 0.7, and the shipped calibration. Standard-read Ollama/GGUF/MLX does not reproduce these scores; no such variant is attached.

Model information sources

Release date ↗ · Weights licence ↗ · Parameter count ↗

HF safetensors metadata for full weights; Strands uses its documented approximate served backbone size. Memory estimate: BF16 weights plus 20% runtime allowance and 2 GB; not a measured requirement.

56.5±1.3#141 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Jebadiah 9B v2.1 (T1e), out of 357 with a score, then more from frontier-infra.

#	model	score	where	RAM	released
141	openjev (DecisionBench ec4ff3df) razorback16	57±2	model files
142	matilda-jev-v1.5 (27B) Maincode	57±4	model files		2026-10-09
143	Jebadiah 9B v2.1 (T1e) frontier-infra	57±1	local	~25GB	2026-10
144	CoCo-Decision-4B 2.4 Corners	57±1	model files		2026-10-16
145	Amber Hybrid 4B (decision readout) MLukauskas	57±1	model files
	more from frontier-infra
57	Jebadiah 27B v2.1 (T1e) frontier-infra	65±1	local	~69GB	2026-10
125	Jebadiah 27B v2.1 (Ollaya Q4_K_M) frontier-infra	59±4	local	~16GB	2026-10
160	Jebadiah 9B v2.1 (Ollaya Q8_0) frontier-infra	55±3	local	~9.1GB	2026-10

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #128 of 250 · 7.3% 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: API-Bank (accuracy) submitted	85.8% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 191/236	easy · avg 70%	▇ 2.2%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	94.5% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 121/246	very easy · avg 92%	▇ 1.8%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	36.4% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 111/243	medium · avg 37%	▇ 1.2%	sharp · at its level · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	80.3% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 142/246	easy · avg 72%	▇ 1.1%	noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	62.1% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 89/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	80.0% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #129 of 258 · 6.7% 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	42.6% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 123/246	medium · avg 38%	▇ 2.5%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	52.7% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 127/246	medium · avg 47%	▇ 2.3%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	74.0% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 117/246	easy · avg 74%	▇ 0.6%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	71.9% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 135/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	85.4% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 81/238	easy · avg 83%	▇ 0.4%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	74.8% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 60/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	13.4% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #131 of 256 · 23% of its score · 9 tests

Trails vLLM-SR d3-nano (2B), JevK5 v0.3, Decider 4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	82.0% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 170/246	easy · avg 74%	▇▇ 5.4%	typical
Decision Index 0.4.1: ANLI (macro-F1) submitted	68.9% ✎	▁▂▃▅▅█▂····▁ beats 148/246	medium · avg 60%	▇▇ 5.4%	at its level
Decision Index 0.4.1: HellaSwag (accuracy) submitted	88.2% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 122/246	very easy · avg 85%	▇▇ 4.9%	sharp
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	54.6% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 156/246	medium · avg 44%	▇ 2.4%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	19.6% ✎	▁··▂▃▃▅▇█▇▃▃ beats 107/246	hard · avg 22%	▇ 1.2%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	71.2% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 80/246	easy · avg 71%	▇ 1.1%	noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	68.3% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 126/246	medium · avg 62%	▇ 1.0%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	74.9% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 128/246	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	89.4% ✎	▁···▁▁▁▁▃▆█▃ beats 141/246	easy · avg 84%	▇ 0.6%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #75 of 247 · 9.5% of its score · 6 tests

Beats Jev 1.13, Quyet-1.0-Large, jev-brain · Gemma-4-31B (decision readout) here, though they rank higher overall. Trails Amber 0.4B, 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	66.9% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 138/246	medium · avg 61%	▇▇ 4.0%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.1% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 153/246	medium · avg 60%	▇ 2.0%	blunt · at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	92.6% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 173/246	easy · avg 83%	▇ 1.1%	sharp · noisy
Decision Index 0.4.1: cfcolor (accuracy) submitted	62.2% ✎	▁········▁▇█ beats 129/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	15.2% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 123/237	hard · avg 21%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	46.5% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 153/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #105 of 263 · 45% of its score · 14 tests

Beats Senova-4B v2, Cerno 9B v1.1, OneJev1.6-4B here, though they rank higher overall. Trails Decider 35B-A3B, decisio 0.4.0 (Qwen3.6-35B-A3B) (decision readout), Solar Decide 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	58.8% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 148/246	medium · avg 46%	▇▇▇▇ 11%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	80.3% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 160/246	easy · avg 70%	▇▇▇ 6.9%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	70.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 136/246	easy · avg 66%	▇▇▇ 6.3%	at its level
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	96.0% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 163/246	very easy · avg 90%	▇ 3.6%	sharp · maxed out
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	46.6% ✎	▁··▄█▆▆▆▅▅▃▁ beats 132/246	medium · avg 45%	▇ 3.6%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	48.0% ✎	▂▆▅▅▆█▆▃▁··▁ beats 180/246	medium · avg 39%	▇ 3.3%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	81.3% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 133/246	easy · avg 78%	▇ 3.1%	typical
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	98.4% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 149/246	very easy · avg 96%	▇ 1.8%	sharp · maxed out · noisy

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	30.7% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 152/246	hard · avg 22%	▇ 1.5%	at its level
Decision Index 0.4.1: MuSR (accuracy) submitted	56.1% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 84/246	medium · avg 60%	▇ 1.2%	blunt · at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	60.7% ✎	██▄▃▃▄▁▁···▁ beats 145/246	medium · avg 58%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	69.1% ✎	▁███▆▅▃▃▁▁▁▁ beats 124/246	easy · avg 71%	▇ 1.0%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	13.8% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 100/246	hard · avg 16%	▇ 0.7%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	9.8% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 28/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 8.5% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	50.5700 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 148/247	avg 41.206 points	▇▇ 5.5%	blunt
Decision Index 0.4.1: private new domains (equated points)	51.3900 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 161/247	avg 38.861 points	▇ 3.0%	blunt

$ where to run it

Other ways to run it

Run it as published · needs ~25.2 GB, NVIDIA only · from huggingface.co/frontier-infra (official)
pip install torch==2.8.0 transformers==5.17.0 accelerate safetensors git+https://github.com/apolinario/decision-index.git@25c6ec7b6b5f44a216c63c3a700de3a9c6d6699d && git clone https://github.com/getainode/jebadiah.git jebadiah-t1e && git -C jebadiah-t1e checkout 678f6e2cc2bb1b51f34407d00255b5e13109ce3f && PYTHONPATH=jebadiah-t1e/eval/decision-index python -c 'from jebadiah_engine import JebadiahEngine; e=JebadiahEngine(model="frontier-infra/jebadiah-9b-v2-1", revision="de19e80e18aa23420be410d54fdee435587eaad3", device="cuda", dtype="bfloat16", repeat_payload=True, reverse_avg_below=0.7, prefix_cache=True, max_batch=64, batch_tokens=32768); print(e("The invoice is overdue.", {"overdue":{"type":"noul","instructions":"Is the invoice overdue?"}}))'

Download model files ↗
Published model files verified. This is a verified repository snapshot; the benchmark does not establish an identical weight revision. See the local setup below for the reviewed runtime. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/frontier-infra ↗

$ 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		= 56.5

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	80.0%	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]	13.4%	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