whatmodel.sh / decision / Tev1-4B-experimental (DecisionBench 0b7becf0)

Tev1-4B-experimental (DecisionBench 0b7becf0)

+ contribute

Tev1-4B-experimental (DecisionBench 0b7becf0) is an open-weights decision model from Together.

Catalogue identity notes

DecisionBench v1 comparison: togethercomputer/Tev1-4B-experimental, revision 0b7becf017daa0e5eb222f8ce7483c8c8259c52f; language-model; adapter tev1-qwen35-single-letter-choice-v1; probability source softmax_over_allowed_option_letter_next_token_logits. Kept separate from newer or unpinned Decision Index recipes; standard prompt, not compact. No unverified runtime or OpenRouter price imported. Current repository metadata checked separately; an unpinned alias is not evidence that today’s weights reproduce this historical run.

55.5±1.5#152 of 355 decision modelsfrom 32 benchmark results across 2 sources

$ how it compares

The decision models ranked either side of Tev1-4B-experimental (DecisionBench 0b7becf0), out of 357 with a score, then more from Together.

#	model	score	where	released
152	open-alternative-jev (DecisionBench 4a85df18) IkerMoel	56±2	source code
153	Open-Jev-9B (DecisionBench 47e96688) ZefanCai	56±2	model files	2026-09-20
154	Tev1-4B-experimental (DecisionBench 0b7becf0) Together	56±2	model files
155	muria (Gemma 4 12B) plantwaterer	55±1	model files
156	Decider 35B-A3B Mapika	55±1	model files	2026-09-20
	more from Together
202	Together Tev1 Qwen3.5-4B Together	51±1	model files
306	Together Tev1 Qwen3.5-0.8B Together	31±1	model files

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

$ what it's good at

workflows▁▁▁▂▁▂▂▆█▄▁▁ #51 of 114 · 99% of its score · 32 tests

Beats Clef-omni, Clef-flash, Bespoke Nimble 9B v3 here, though they rank higher overall. Trails StartLux-Decision v1.1 0.8B, Together Tev1 Qwen3.5-4B, Jebadiah 9B v2.1 (Ollaya Q8_0) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
DecisionBench v1 · action selection (all-request accuracy) submitted	56.1% ✎	▂▁▂▃▄▃▁▁▂█▇▄ beats 33/56	medium · avg 51%	▇▇▇▇▇▇▇ 16%	at its level
DecisionBench v1 · routing (all-request accuracy) submitted	69.3% ✎	▁▁▁▁▂▂▁▁▁▁▃█ beats 30/56	medium · avg 64%	▇▇▇▇ 11%	sharp · at its level
DecisionBench v1 · navigation (all-request accuracy) submitted	66.0% ✎	▁▁·▃▁▁▁▁▁▁▃█ beats 28/56	medium · avg 58%	▇▇▇▇ 8.8%	sharp · at its level
DecisionBench v1 · record classification (all-request accuracy) submitted	46.0% ✎	▃▂▁▂▂▂▄▁▃▆██ beats 40/56	medium · avg 39%	▇▇▇ 7.5%	at its level
DecisionBench v1 · verification (all-request accuracy) submitted	59.0% ✎	▁▁▅▁▃▂▂▁▁▇▇█ beats 32/56	medium · avg 56%	▇▇ 5.1%	blunt · at its level
Prevalence study · CLINC150	96.4% ✎	██·········█ beats 1/2	very easy · avg 95%	▇▇ 4.8%	sharp · maxed out · small run
Prevalence study · TREC-6	88.9% ✎	█··█·······█ beats 1/2	easy · avg 84%	▇▇ 4.6%	sharp · small run
DecisionBench v1 · document record classification (all-request accuracy) submitted	56.2% ✎	▂▂·▁▂▄▃▆▄█▁▁ beats 48/56	medium · avg 46%	▇▇ 4.2%	at its level

24 more tests

test	result	vs the others in its run	difficulty	counts	why
Prevalence study · FPB	73.5% ✎	█·········██ beats 1/2	medium · avg 60%	▇ 3.6%	at its level · small run
DecisionBench v1 · rubric scoring prioritization (all-request accuracy) submitted	46.4% ✎	▁▁▅▅▃▃▅█▃▃·▁ beats 34/56	medium · avg 45%	▇ 3.5%	at its level
DecisionBench v1 · triage (all-request accuracy) submitted	80.0% ✎	▁·▁·▂▃▄▃▂█▄▂ beats 30/56	easy · avg 78%	▇ 3.5%	sharp
DecisionBench v1 · completion assessment (all-request accuracy) submitted	88.0% ✎	▁▁▂▃▄·▂▁▁▆█▂ beats 26/56	very easy · avg 86%	▇ 3.3%	sharp
Prevalence study · HWU64	89.5% ✎	█··········▄ beats 0/2	very easy · avg 86%	▇ 3.0%	small run
Prevalence study · HateXplain	45.8% ✎	█·█········█ beats 0/2	medium · avg 37%	▇ 2.9%	at its level · small run
DecisionBench v1 · bounded extraction (all-request accuracy) submitted	93.3% ✎	▃▃▂·▁▁▁▁▁▁█▅ beats 32/56	very easy · avg 86%	▇ 2.8%	sharp · noisy
DecisionBench v1 · content classification (all-request accuracy) submitted	79.0% ✎	▁····▁▁▁▁▁▁█ beats 33/56	easy · avg 73%	▇ 2.6%	typical
DecisionBench v1 · review scoring (all-request accuracy) submitted	56.0% ✎	▁······▂▃▅▇█ beats 33/56	medium · avg 52%	▇ 2.3%	at its level
DecisionBench v1 · retrieval ranking (all-request accuracy) submitted	19.0% ✎	▁▁·▁▁▂▃▃▃▁▁█ beats 23/56	medium · avg 35%	▇ 1.9%	at its level · noisy
DecisionBench v1 · target selection (all-request accuracy) submitted	16.0% ✎	▁▁·▁▁▁▃▁▃▁▁█ beats 23/56	hard · avg 29%	▇ 1.7%	at its level · noisy
DecisionBench v1 · risk scoring (all-request accuracy) submitted	69.0% ✎	▁▁·▁▂▂▁▃▃█▇▃ beats 47/56	medium · avg 62%	▇ 1.6%	blunt · at its level
DecisionBench v1 · reasoning (all-request accuracy) submitted	54.3% ✎	▂·▁▁▆█▅▃▃▂▁▁ beats 38/56	medium · avg 52%	▇ 1.0%	at its level
DecisionBench v1 · document workflows (all-request accuracy) submitted	75.7% ✎	█▄▃▁▁▃▂▂▁·▁▁ beats 43/56	easy · avg 66%	▇ 0.6%	blunt · at its level
DecisionBench v1 · retrieval verification (all-request accuracy) submitted	86.9% ✎	█▁▂▁▁▁▁▁▂▅▁▁ beats 42/56	easy · avg 74%	▇ 0.6%	noisy
DecisionBench v1 · guardrails moderation (all-request accuracy) submitted	60.9% ✎	▁▁▁▂▆▃▃█···▁ beats 36/56	medium · avg 52%	▇ 0.4%	blunt · at its level · noisy
DecisionBench v1 · safety gating (all-request accuracy) submitted	94.0% ✎	▂·····▆█▂▂▄▇ beats 39/56	easy · avg 77%	▇ 0.3%	noisy
DecisionBench v1 · document classification (all-request accuracy) submitted	11.0% ✎	▂▁·▂▁▁▁▄▁▂▂█ beats 19/56	hard · avg 21%	▇ 0.3%	blunt · noisy
DecisionBench v1 · semantic filtering (all-request accuracy) submitted	84.0% ✎	▁·▁▁·▁▁█▂▃█▂ beats 43/56	easy · avg 71%	▇ 0.2%	blunt · at its level · noisy
DecisionBench v1 · content moderation (all-request accuracy) submitted	100.0% ✎	▁····▃▅▃▂▂·█ beats 46/56	easy · avg 82%	▇ 0.1%	noisy
DecisionBench v1 · context management (all-request accuracy) submitted	92.0% ✎	▁·····▁▇▆▁█▃ beats 50/56	easy · avg 73%	▇ 0.1%	blunt · noisy
DecisionBench v1 · entity alignment (all-request accuracy) submitted	50.6% ✎	▁·▁▄▇▄▅▄▂▁▄█ beats 25/56	easy · avg 66%	▇ 0.1%	at its level · noisy
DecisionBench v1 · function agent skill routing (all-request accuracy) submitted	49.2% ✎	▃▃▄▅▆▂▅▄▃▄█▃ beats 19/56	easy · avg 68%	▇ 0.1%	blunt · at its level · noisy
DecisionBench v1 · routing triage (all-request accuracy) submitted	0.0% ✎	█▁···▁·▂▆▅▂▂ beats 1/56	medium · avg 42%	▇ 0.0%	blunt · at its level · noisy

$ where to run it

Download model files ↗
Published model files verified. This is the revision recorded by the benchmark. 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/togethercomputer ↗

$ how the score was worked out · Hanno Labs DecisionBench v1 r… 80%, Typed Decision Models under P… 19%

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
Hanno Labs DecisionBench v1 reviewed results · submitted; independent execution unverified	27	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 80%	CC0 1.0
Typed Decision Models under Prevalence Shift: Decision Training, Calibration, and Implicit Priors	5	▇▇▇▇▇▇ 19%	CC-BY-4.0
prior · pull toward the middle		▇ 1%
weighted average		= 55.5

$ 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