whatmodel.sh / decision / Qwen-2.5-1B-RLCD (decision readout)

Qwen-2.5-1B-RLCD (decision readout)

+ contribute

Qwen-2.5-1B-RLCD (decision readout) is a source-available decision implementation from harshatheg. Its published size is 1.54B parameters.

Catalogue identity notes

Exact Decision Index tested engine harsha; reported model Qwen-2.5-1B-RLCD. Type: inference technique; technique: autoregressive. Implementation: https://huggingface.co/harshatheg/Qwen-2.5-1B-RLCD. Comparison entry; no current run command, API price or speed inferred from the benchmark.

Model information sources

· Parameter count ↗

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

21.4±1.1#337 of 355 decision modelsfrom 42 benchmark results across 1 source

$ how it compares

The decision models ranked either side of Qwen-2.5-1B-RLCD (decision readout), out of 357 with a score.

#	model	score	where
337	Prumo (rule-based engine) tardellirs	23±1	source code
338	gliner2.5-small-v1 (DecisionBench 7e6f537f) Fastino	23±2	model files
339	Qwen-2.5-1B-RLCD (decision readout) harshatheg	21±1	source code
340	Laya ConvAI Innovations	21±1	model files
341	Verdict heman10x	21±1	model files

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

$ what it's good at

tools & automation▁▃▃▁▁▂▃▄▆██▆ #229 of 250 · 10% of its score · 6 tests

Beats DM-JEPA 1.1, JEV FLAN-T5 Large public v2 (342M), Bekko System One v0 400M here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	47.4% ✎	▁▂▃▁▁▂▂▄▅▆█▁ beats 21/246	very easy · avg 92%	▇▇▇ 6.9%	sharp · at its level · noisy
Decision Index 0.4.1: API-Bank (accuracy) submitted	4.3% ✎	▁▁▁▃▁▁▁▂▃▂█▂ beats 11/236	easy · avg 70%	▇ 1.6%	sharp · noisy
Decision Index 0.4.1: When2Call (accuracy) submitted	22.0% ✎	▁▃▁▂▃▅▅▆█▇█▃ beats 8/246	easy · avg 72%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	8.5% ✎	▃▁▁▁▁·▁▁▁▄█▁ beats 0/246	medium · avg 60%	▇ 0.7%	blunt · at its level
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	0.0% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 24/243	medium · avg 37%	▇ 0.1%	sharp · too hard for it · noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	58.9% ✎	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▁▃▁·▁▁▁▁▃▃█▅ #256 of 258 · 4.5% of its score · 7 tests

Beats JevK5 Lite here, though they rank higher overall. Trails Zev (decision readout), LFM2.5-350M-RLCD, Nirnaya 0.4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	8.9% ✎	▁▁▃▁▁▁▂▂▃▃█▅ beats 2/246	medium · avg 47%	▇ 1.2%	at its level
Decision Index 0.4.1: BRIGHT (nDCG@10) submitted	14.3% ✎	▁▁▁▃▁▁▁▂▂▄▇█ beats 9/246	medium · avg 38%	▇ 1.2%	blunt
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	1.2% ✎	▁▃▁▁▁▁▁▂▃▆█▄ beats 3/238	easy · avg 83%	▇ 0.6%	sharp · at its level · noisy
Decision Index 0.4.1: HoVer (accuracy) submitted	50.1% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 3/246	easy · avg 74%	▇ 0.6%	blunt · at its level
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	49.0% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 6/245	easy · avg 70%	▇ 0.5%	at its level · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	2.6% ✎	▁·▃▁▁▁▁▁▂█▇█ beats 3/238	easy · avg 79%	▇ 0.4%	at its level · noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	46.4% ✎	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▂▃▂▃▂▅▆▃█▆▄▃ #234 of 256 · 23% of its score · 9 tests

Beats Crivo-68M, Bosun v3.1 1.7B LoRA, Mola-68M 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	42.5% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 22/246	very easy · avg 85%	▇▇▇▇ 9.2%	sharp · at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	43.7% ✎	▁▁▃▂▂▃▃▄▇▇█▄ beats 8/246	easy · avg 74%	▇▇ 5.6%	at its level
Decision Index 0.4.1: ANLI (macro-F1) submitted	28.2% ✎	▁▃▃▅▅█▂····▁ beats 9/246	medium · avg 60%	▇ 3.5%	at its level
Decision Index 0.4.1: FinEntity (macro-F1) submitted	43.3% ✎	▁···▁▁▃▁▃▆█▃ beats 13/246	easy · avg 84%	▇ 1.1%	at its level · noisy
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	26.7% ✎	▁▁▁▃▁▁▁▂▂▇▇█ beats 11/246	easy · avg 71%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	24.3% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 32/246	medium · avg 44%	▇ 0.9%	typical
Decision Index 0.4.1: VAST (macro-F1) submitted	31.4% ✎	▁▁▃▂▅▄▄▂▄▆█▄ beats 8/246	medium · avg 62%	▇ 0.7%	at its level
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	0.6% ✎	▃▁▁▁▁▁▁▁▁▃▆█ beats 2/246	easy · avg 66%	▇ 0.6%	at its level · noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ACOS (per-review F1) submitted	4.6% ✎	▁··▂▃▃▅▇█▇▃▃ beats 22/246	hard · avg 22%	▇ 0.2%	too hard for it · noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #182 of 247 · 7.1% of its score · 6 tests

Beats Sieve 9B, Kev 9B v2, vLLM-SR d3-nano (2B) here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: New Yorker (accuracy) submitted	19.3% ✎	▃▁▂▃▃▃▇▅█▅▃▁ beats 3/246	medium · avg 61%	▇ 2.7%	at its level
Decision Index 0.4.1: BPoMP (accuracy) submitted	68.1% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 65/246	easy · avg 83%	▇ 1.9%	sharp · at its level · noisy
Decision Index 0.4.1: Humicroedit (accuracy) submitted	50.7% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 25/246	medium · avg 60%	▇ 1.4%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	50.2% ✎	▁········▁▇█ beats 20/246	medium · avg 60%	▇ 0.8%	blunt · at its level
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	38.5% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 46/246	medium · avg 47%	▇ 0.2%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	2.9% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 60/237	hard · avg 21%	▇ 0.1%	sharp · too hard for it · noisy

knowledge & reasoning▁▃▂▂▂▃▃▅▅▆█▂ #243 of 263 · 49% of its score · 14 tests

Beats Amber 0.4B, Dinah-1, Crivo-68M here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	56.5% ✎	▁▁▃▁▂▂▂▂▃▆█▅ beats 17/246	very easy · avg 96%	▇▇▇▇▇▇ 15%	sharp · at its level · noisy
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	43.7% ✎	▂▂▃▂▂▂▁▃▄▆█▆ beats 22/246	very easy · avg 90%	▇▇▇▇ 10%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	36.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 27/246	easy · avg 70%	▇▇ 5.8%	sharp · at its level
Decision Index 0.4.1: BBH (accuracy) submitted	33.7% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 11/246	easy · avg 66%	▇▇ 4.7%	at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	50.4% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 8/246	easy · avg 78%	▇▇ 3.8%	at its level
Decision Index 0.4.1: MMLU-Pro (accuracy) submitted	11.5% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 2/246	medium · avg 46%	▇ 3.4%	sharp
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	28.1% ✎	▂▆▅▅▆█▆▃▁··▁ beats 46/246	medium · avg 39%	▇ 1.6%	blunt
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	18.3% ✎	▁··▄█▆▆▆▅▅▃▁ beats 18/246	medium · avg 45%	▇ 1.0%	sharp

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	37.8% ✎	▃▁▂█▅▄▁▁▁▁▁▁ beats 5/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: CLadder (accuracy) submitted	50.3% ✎	▁███▆▅▃▃▁▁▁▁ beats 14/246	easy · avg 71%	▇ 0.9%	at its level
Decision Index 0.4.1: CRUXEval (accuracy) submitted	35.8% ✎	██▄▃▃▄▁▁···▁ beats 29/246	medium · avg 58%	▇ 0.7%	at its level · noisy
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	2.4% ✎	▁▁▁▃▁▁▁▂▅█▂▁ beats 22/246	hard · avg 22%	▇ 0.3%	too hard for it
Decision Index 0.4.1: ChessBench (accuracy) submitted	8.8% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 43/246	hard · avg 16%	▇ 0.2%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	17.2% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 233/246	very hard · avg 13%	▇ 0.0%	blunt

other tests2 not in a task · 5.9% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	5.2300 points ✎	▃▂▂▃▃▃▄▅▅▇█▃ beats 9/247	avg 41.206 points	▇▇ 3.8%	blunt
Decision Index 0.4.1: private new domains (equated points)	11.7800 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 32/247	avg 38.861 points	▇ 2.1%	blunt

$ where to run it

Implementation and setup instructions ↗
Published implementation files verified; this repository contains no standalone model weights. Consult its setup instructions for dependencies and base weights. Hardware compatibility has not been verified. Source · checked 2026-10-31.

Model repository and documentation: huggingface.co/harshatheg ↗

$ how the score was worked out · Decision Index 0.4.1 100%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 100%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 21.4

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	58.9%	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]	46.4%	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