whatmodel.sh / decision / Surogate Rune 26B-A4B v3

Surogate Rune 26B-A4B v3

+ contribute

Surogate Rune 26B-A4B v3 is an open-weights decision model from Surogate. Its published size is 25.81B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact Decision Index tested engine rune-26b-a4b-v3; reported model Surogate Rune 26B-A4B v3. Type: full fine-tune; technique: autoregressive. Published checkpoint/base reference: bd4a7cbbed66af1a95dfbac12cabf52e6e677411. Implementation: https://github.com/invergent-ai/surogate. Comparison entry; no current run command, 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.

Model information sources

· Weights licence ↗ · Parameter count ↗

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

61.1±1.2#100 of 355 decision modelsfrom 58 benchmark results across 3 sources

$ how it compares

The decision models ranked either side of Surogate Rune 26B-A4B v3, out of 357 with a score.

#	model	score	where
98	GEV-26B-Decide AutoTrust AI Lab	61±1	model files
99	litjev (DecisionBench 1d4bf0f2) zhengxuyu	61±2	model files
100	Surogate Rune 26B-A4B v3 Surogate	61±1	request access
101	Verdin-4B v1.1 victorbennett	61±1	model files
102	garas (Gemma 4 31B) plantwaterer	61±1	model files

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

$ what it's good at

tools & automation▁▃▁▁▁▂▃▄▆██▆ #122 of 250 · 5.6% of its score · 6 tests

Beats Tern-35B-A3B, GEV-26B-Decide 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	83.3% ✎	▁▁▁▁▁▁▁▂▃▂█▂ beats 136/236	easy · avg 70%	▇ 1.7%	sharp · noisy
Decision Index 0.4.1: BFCL (case exact accuracy) submitted	94.8% ✎	▁▂▁▁▁▂▂▄▅▆█▁ beats 127/246	very easy · avg 92%	▇ 1.1%	sharp · maxed out · noisy
Decision Index 0.4.1: Home appliance simulator (case exact accuracy) submitted	46.6% ✎	█▁▁▃▄▄▆▄▁▂▁▃ beats 126/243	medium · avg 37%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: ToolRet (nDCG@10) submitted	64.4% ✎	▁▁▁▁▁·▁▁▁▄█▁ beats 122/246	medium · avg 60%	▇ 0.9%	blunt · at its level
Decision Index 0.4.1: When2Call (accuracy) submitted	76.0% ✎	▁▁▁▂▃▅▅▆█▇█▃ beats 118/246	easy · avg 72%	▇ 0.9%	noisy
Decision Index 0.4.1: RouterBench (selected quality (quality objective)) submitted	79.9% ✎	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▁▁▁·▁▁▁▁▃▃█▅ #91 of 258 · 6.0% of its score · 7 tests

Beats AutoTrust-JEV-27B v1.1, Decider 31B (NVFP4), Jev 1.13 here, though they rank higher overall. Trails Jev-Style 2B v4, Sieve 2B v3, StartLux-Decision v1.1 0.8B 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	46.3% ✎	▁▁▁▁▁▁▁▂▂▄▇█ beats 171/246	medium · avg 38%	▇ 2.3%	blunt · at its level
Decision Index 0.4.1: Amazon ESCI (macro-F1) submitted	55.3% ✎	▁▁▁▁▁▁▂▂▃▃█▅ beats 157/246	medium · avg 47%	▇ 2.1%	at its level
Decision Index 0.4.1: HoVer (accuracy) submitted	80.7% ✎	▆▆▇▅▄▄▃▇▄█▆▄ beats 149/246	easy · avg 74%	▇ 0.5%	blunt
Decision Index 0.4.1: PhishNChips phishing decisions (accuracy) submitted	80.9% ✎	█▅▅▄▃▂▁▁▁▁·▁ beats 175/245	easy · avg 70%	▇ 0.5%	noisy
Decision Index 0.4.1: CLINC150+OOS (macro-F1) submitted	87.4% ✎	▁▁▁▁▁▁▁▂▃▆█▄ beats 96/238	easy · avg 83%	▇ 0.3%	sharp · noisy
Decision Index 0.4.1: BANKING77 (macro-F1) submitted	83.8% ✎	▁·▁▁▁▁▁▁▂█▇█ beats 127/238	easy · avg 79%	▇ 0.3%	noisy
Decision Index 0.4.1: SGD/SGD-X (macro-F1) submitted	66.4% ✎	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▂▂▂▃▂▅▆▃█▆▄▃ #105 of 256 · 19% of its score · 9 tests

Beats jev-brain · Gemma-4-31B (decision readout), AnyJev L0 · Gemma-4-31B (decision readout), decisio 0.6.0 (Gemma 4 31B) (decision readout) here, though they rank higher overall. Trails Decider 4B, jiwo 4B v2, Sieve 4B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: ANLI (macro-F1) submitted	73.5% ✎	▁▂▃▅▅█▂····▁ beats 182/246	medium · avg 60%	▇▇ 4.6%	at its level
Decision Index 0.4.1: NLI4CT (macro-F1) submitted	80.4% ✎	▁▁▁▂▂▃▃▄▇▇█▄ beats 155/246	easy · avg 74%	▇▇ 4.5%	typical
Decision Index 0.4.1: HellaSwag (accuracy) submitted	92.4% ✎	▂▄▂▂▄▇▃▇█▅▃▁ beats 146/246	very easy · avg 85%	▇ 3.3%	sharp · maxed out
Decision Index 0.4.1: iSarcasmEval (Sarcasm F1 · track A, English) submitted	60.4% ✎	▁·▁·▁▁▂▄▅█▇▄ beats 187/246	medium · avg 44%	▇ 2.2%	at its level
Decision Index 0.4.1: ACOS (per-review F1) submitted	26.8% ✎	▁··▂▃▃▅▇█▇▃▃ beats 152/246	hard · avg 22%	▇ 1.3%	at its level · noisy
Decision Index 0.4.1: VAST (macro-F1) submitted	76.6% ✎	▁▁▁▂▅▄▄▂▄▆█▄ beats 179/246	medium · avg 62%	▇ 0.9%	at its level
Decision Index 0.4.1: ContractNLI (macro-F1) submitted	77.0% ✎	▁▁▁▁▁▁▁▂▂▇▇█ beats 134/246	easy · avg 71%	▇ 0.9%	noisy
Decision Index 0.4.1: RAGTruth (F1 on hallucinated class) submitted	76.8% ✎	▁▁▁▁▁▁▁▁▁▃▆█ beats 142/246	easy · avg 66%	▇ 0.6%	noisy

1 more test

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: FinEntity (macro-F1) submitted	88.4% ✎	▁···▁▁▁▁▃▆█▃ beats 128/246	easy · avg 84%	▇ 0.5%	noisy

arts & human taste▁▇▄▃▅▅█▅▄▂▁▁ #113 of 247 · 8.3% of its score · 6 tests

Beats Bobcat 1.3 (31B), Nace.AI Drex v2.0 (35B-A3B), decisio 0.6.0 (Gemma 4 31B) (decision readout) here, though they rank higher overall. Trails vLLM-SR vela3-fast-vision (Vela 3.0, 0.25B), Crivo-400M, 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: New Yorker (accuracy) submitted	74.1% ✎	▁▁▂▃▃▃▇▅█▅▃▁ beats 182/246	medium · avg 61%	▇ 3.4%	at its level
Decision Index 0.4.1: Humicroedit (accuracy) submitted	62.2% ✎	▁·▁▃▂▂▅█▄▂▁▁ beats 158/246	medium · avg 60%	▇ 1.8%	blunt · at its level
Decision Index 0.4.1: cfcolor (accuracy) submitted	63.1% ✎	▁········▁▇█ beats 148/246	medium · avg 60%	▇ 1.0%	blunt · at its level
Decision Index 0.4.1: POP909-CL (accuracy) submitted	66.8% ✎	▄▅▅▃▆▅▃▅▂▅▃█ beats 191/237	hard · avg 21%	▇ 1.0%	sharp · at its level · noisy
Decision Index 0.4.1: BPoMP (accuracy) submitted	89.6% ✎	▁█▄▄▅█▆▅▄▁▁▁ beats 134/246	easy · avg 83%	▇ 0.9%	sharp · noisy
Decision Index 0.4.1: Habermas Machine (accuracy) submitted	42.2% ✎	▁▂▄█▇▅▁▁▄▄▁▁ beats 99/246	medium · avg 47%	▇ 0.3%	blunt · at its level

knowledge & reasoning▁▂▂▂▂▃▃▅▅▆█▂ #71 of 263 · 37% of its score · 14 tests

Beats StartLux-Decision v1.1 9B, Sieve 27B v2, RSI-Jev v6.1 VL 27B (effort auto) here, though they rank higher overall. Trails Solar Decide, Clef-flash, Clef-omni 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	67.2% ✎	▄▄▃▃▂▄▅▇██▅▁ beats 191/246	medium · avg 46%	▇▇▇▇ 9.4%	sharp · at its level
Decision Index 0.4.1: MMLU (accuracy) submitted	83.9% ✎	▁▄▄▃▃▂▅▇▅█▇▁ beats 176/246	easy · avg 70%	▇▇ 5.4%	sharp
Decision Index 0.4.1: BBH (accuracy) submitted	81.2% ✎	▄▆▄▄█▇▇▄▃▁▁▁ beats 199/246	easy · avg 66%	▇▇ 5.2%	typical
Decision Index 0.4.1: GSM8K (accuracy (4- and 10-choice)) submitted	77.1% ✎	▁··▄█▆▆▆▅▅▃▁ beats 218/246	medium · avg 45%	▇ 3.1%	sharp · at its level
Decision Index 0.4.1: GPQA Diamond (accuracy) submitted	46.9% ✎	▂▆▅▅▆█▆▃▁··▁ beats 168/246	medium · avg 39%	▇ 3.1%	blunt · at its level
Decision Index 0.4.1: WinoGrande (accuracy) submitted	86.0% ✎	█▅█▅▄█▆▄▃▃▁▁ beats 169/246	easy · avg 78%	▇ 2.5%	typical
Decision Index 0.4.1: ARC-Challenge (accuracy) submitted	96.8% ✎	▂▂▂▂▂▂▁▃▄▆█▆ beats 188/246	very easy · avg 90%	▇ 2.2%	sharp · maxed out
Decision Index 0.4.1: SATA-Bench (case exact accuracy) submitted	34.8% ✎	▁▁▁▁▁▁▁▂▅█▂▁ beats 205/246	hard · avg 22%	▇ 1.5%	at its level

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: MuSR (accuracy) submitted	64.9% ✎	▁▁▂█▅▄▁▁▁▁▁▁ beats 175/246	medium · avg 60%	▇ 1.1%	blunt · at its level
Decision Index 0.4.1: ARC-Easy (accuracy) submitted	99.0% ✎	▁▁▂▁▂▂▂▂▃▆█▅ beats 200/246	very easy · avg 96%	▇ 1.0%	sharp · maxed out · noisy
Decision Index 0.4.1: CRUXEval (accuracy) submitted	74.4% ✎	██▄▃▃▄▁▁···▁ beats 182/246	medium · avg 58%	▇ 1.0%	at its level · noisy
Decision Index 0.4.1: CLadder (accuracy) submitted	72.7% ✎	▁███▆▅▃▃▁▁▁▁ beats 144/246	easy · avg 71%	▇ 0.8%	typical
Decision Index 0.4.1: ChessBench (accuracy) submitted	18.7% ✎	▄▇▄▄▄▆▄█▄▁▁▁ beats 159/246	hard · avg 16%	▇ 0.7%	blunt
Decision Index 0.4.1: HLE (accuracy) submitted	10.6% ✎	▁▁▂▃▆█▇▅▅▃▁▁ beats 53/246	very hard · avg 13%	▇ 0.0%	blunt

vision▁·▃▂▃▃▇▄▄█▄▃ #45 of 79 · 13% of its score · 14 tests

Trails LiquidAI d1-3B, JPT-9B Qwen3.5-9B LoRA, Solomon v1.1 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	63.8200 points ✎	▁·▁▁▃▁▄▄▃▅█▂ beats 18/61	avg 63.423 points	▇ 1.5%	blunt
Decision Index Vision 0.4 · MMMU-Pro vision (chance-corrected points) submitted	30.7200 points ✎	▁▁▅▁▄▁▄█▄▃▇▇ beats 30/61	avg 22.797 points	▇ 1.4%	blunt
Decision Index Vision 0.4 · Winoground (chance-corrected points) submitted	78.5000 points ✎	▁·▁▁▁▁·▂▁▃▅█ beats 27/61	avg 66.987 points	▇ 1.3%	blunt
Decision Index Vision 0.4: private same skills (points)	51.9900 points ✎	▁▁▃▃▁▂▄▆▃▃▅█ beats 24/61	avg 48.067 points	▇ 1.3%	blunt
Decision Index Vision 0.4 · Moderation (Hateful Memes) (chance-corrected points) submitted	38.1700 points ✎	▆▃▃▆▄▄▇██▁▆▆ beats 33/61	avg 28.443 points	▇ 1.1%	blunt
Decision Index Vision 0.4 · RealWorldQA (chance-corrected points) submitted	54.2200 points ✎	▁·▂▂▁▃▃▅▅▃▂█ beats 17/61	avg 53.651 points	▇ 1.0%	blunt
Decision Index Vision 0.4 · CharXiv (chance-corrected points) submitted	73.4300 points ✎	▂▁▁▁▁▃▁▅▅▆██ beats 34/61	avg 62.137 points	▇ 1.0%	blunt
Benchmark Heaven imagejevbench v0.3.0: intelligence (points)	44.8023 points ✎	▃·▃▃··▅█▅▅·▃ beats 9/12	avg 32.235 points	▇ 0.9%	blunt

6 more tests

test	result	vs the others in its run	difficulty	counts	why
Decision Index Vision 0.4 · InfographicVQA (chance-corrected points) submitted	89.6200 points ✎	▁·▁▂▁▁▃▁▃▂▅█ beats 25/61	avg 83.859 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · R-Bench-M (chance-corrected points) submitted	33.2200 points ✎	▂▄▇▆█▄▄▇▂··▁ beats 45/61	avg 19.676 points	▇ 0.8%	blunt
Decision Index Vision 0.4 · BLINK (chance-corrected points) submitted	53.1200 points ✎	▁···▁▂▂▂█▄▂▃ beats 26/61	avg 44.994 points	▇ 0.7%	blunt
Decision Index Vision 0.4 · CV-Bench (chance-corrected points) submitted	70.2100 points ✎	▁▁▁▁▂▁▁▃▄█▃▃ beats 18/61	avg 67.662 points	▇ 0.6%	blunt
Decision Index Vision 0.4 · KIE (CORD+FUNSD) (chance-corrected points) submitted	90.9800 points ✎	▁··▁▁▁▁▁▂▄█▁ beats 27/61	avg 85.184 points	▇ 0.4%	blunt
Benchmark Heaven imagejevbench v0.3.0: calibration (points)	84.8124 points ✎	▃···▃·▅█▅▃▃▅ beats 11/12	avg 68.584 points	▇ 0.4%	blunt

other tests4 not in a task · 11% of its score

test	result	vs the others in its run	difficulty	counts	why
Decision Index 0.4.1: private same skills (equated points)	56.7000 points ✎	▂▂▂▃▃▃▄▅▅▇█▃ beats 185/247	avg 41.206 points	▇▇ 5.1%	blunt
Decision Index 0.4.1: private new domains (equated points)	56.0000 points ✎	▃█▃▃▂▆▃▃▄▄▄▄ beats 173/247	avg 38.861 points	▇ 2.8%	blunt
Benchmark Heaven jevbench v1.6.1: intelligence (points)	56.0557 points ✎	▃···▃·▃▃█▅▅█ beats 5/13	avg 32.166 points	▇ 2.2%	blunt
Benchmark Heaven jevbench v1.6.1: calibration (points)	90.8804 points ✎	▂······▂▆▂██ beats 11/13	avg 70.133 points	▇ 0.6%	blunt

$ where to run it

Request access to model files ↗
Gated files: the publisher requires access approval. 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/surogate ↗

$ how the score was worked out · Decision Index 0.4.1 84%, Decision Index Vision 0.4 12%, Benchmark Heaven (own decisio… 4%

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	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 84%	CC BY 4.0
Decision Index Vision 0.4 · submitted; independent execution unverified	12	▇▇▇▇ 12%	CC BY 4.0
Benchmark Heaven (own decision evaluations)	4	▇ 4%	CC BY 4.0
prior · pull toward the middle		▇ 1%
weighted average		= 61.1

not counted (2)

Decision Index 0.4.1	Decision Index 0.4.1: RouterBench (selected quality (quality objective)) [correct]	79.9%	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]	66.4%	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