Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Winnow-12B Q8

Other · 12B

Strongest in Routing & classification (#18 of 85), weakest in Calibration (#45 of 85). Above par in 3 of 3 scopes. Among the models it meets almost everywhere, it finishes behind DeepSeek V4.1 Flash and GPT-6 Luna and ahead of Decider 35B A3B and Decision 2B.

§ 1 · Profile

What it is good at

Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.

Decisions53.6#27/85
Routing & classification55.3#18/85
Calibration52#45/85

§ 2 · Head to head

What it beats, and what beats it

The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for Winnow-12B Q8, left for the other.

Laya 322Mwon 2 · lost 0
Djev Sparkwon 2 · lost 0
Mirrorwon 3 · lost 0
Raw Qwen3 0.6B direct logitswon 3 · lost 0
GLiNER2won 3 · lost 0
GLiNER2 largewon 3 · lost 0
Raw Qwen3 1.7B direct logitswon 3 · lost 0
CLM 8Bwon 3 · lost 0
SimpleJevwon 3 · lost 0
GLiNER2.5 smallwon 3 · lost 0
Raw Qwen3 8B direct logitswon 3 · lost 0
Open Jev JSON Canvaswon 3 · lost 0
openJev Verdictwon 3 · lost 0
Raw Qwen3 4B Instruct direct logitswon 3 · lost 0
System Onewon 3 · lost 0
GLiNER2.5 multiwon 3 · lost 0
kev 0.5Bwon 3 · lost 0
Decider 2Bwon 3 · lost 0
kev 4Bwon 3 · lost 0
kev 8Bwon 3 · lost 0
JevActwon 3 · lost 0
Smalljev semantic-v9won 3 · lost 0
kev 0.6Bwon 3 · lost 0
OpenDecisionwon 3 · lost 0
Spark S1 4B V6won 3 · lost 0
Malkuth 2Bwon 3 · lost 0
Typecastlmwon 3 · lost 0
Open Alternative Jevwon 3 · lost 0
Open-Jev 2Bwon 3 · lost 0
Layawon 3 · lost 0
System One Openwon 3 · lost 0
Raw Phi-4 mini direct logitswon 3 · lost 0
OpenSourceJevwon 3 · lost 0
Bespoke Nimble 9Bwon 3 · lost 0
Malkuth 4Bwon 3 · lost 0
SimpleJev Qwen3.6-35B-A3Bwon 3 · lost 0
Open-Jev 9Bwon 3 · lost 0
Qwen3.5-9B Jev-like data-mix v2won 3 · lost 0
Jev Localwon 3 · lost 0
Jev Omniwon 3 · lost 0
Verdict Smallwon 2 · lost 1
Alibaba GTE Reranker ModernBERT-basewon 2 · lost 1
Certo v1won 2 · lost 1
Mixedbread mxbai-rerank-base-v2won 2 · lost 1
BAAI bge-reranker-v2-m3won 2 · lost 1
Open Jev Deberta V3 Largewon 2 · lost 1
Qwen3.5-0.8B Decision Modelwon 2 · lost 1
openJev Verdict 1.4won 2 · lost 1
Decision Fastwon 2 · lost 1
Jeffwon 2 · lost 1
Lev 350Mwon 2 · lost 1
Vonwon 2 · lost 1
Decision Machine 1won 2 · lost 1
Qwen3 Reranker 4Bwon 2 · lost 1
Jobe Qwen3.5-4Bwon 2 · lost 1
SemIfwon 2 · lost 1
Metask Jev 4Bwon 2 · lost 1
Standard One 8Bwon 2 · lost 1
Decision 2Bwon 2 · lost 1
Decider 35B A3Bwon 2 · lost 1
JEV Qwen3.5-9B Base NVFP4won 1 · lost 2
Gemini 3.1 Flash Litewon 1 · lost 2
OpenJevwon 1 · lost 2
ZeroEntropy zerank-2won 1 · lost 2
local-jev Qwen3.5-4Bwon 1 · lost 2
Jqvwon 1 · lost 2
reflex 4Bwon 1 · lost 2
LitJevwon 1 · lost 2
Reflex 27Bwon 1 · lost 2
JevOnewon 1 · lost 2
Hopperwon 1 · lost 2
Gemma 4 31Bwon 0 · lost 2
Openjev Sglangwon 0 · lost 3
JevK5 v0.2.0won 0 · lost 3
swanOnewon 0 · lost 3
Decider-4b v2won 0 · lost 3
Cygnetwon 0 · lost 3
SimpleJev Qwen3.8-27Bwon 0 · lost 3
NInfer Qwen3.8-27B NVFP4won 0 · lost 3
NInfer Qwen3.8-Flash-Next mixedwon 0 · lost 3
Jev 1.13.0won 0 · lost 3
Instinctwon 0 · lost 3
Gemma 4 31B IT (Autoloops)won 0 · lost 3
Djevwon 0 · lost 3
GPT-5.6 Lunawon 0 · lost 3
GPT-6 Lunawon 0 · lost 3
DeepSeek V4.1 Flashwon 0 · lost 3

§ 3 · Sources

Where the numbers come from

1 publication, 2 figures. Every one links to the page it was read from.

JevBench ↗2 measuresread 2026-09-26
JevBench · Intelligence 48.3%JevBench · Calibration 64.8%

Badge

PublicAI Index badge for Winnow-12B Q8[![PublicAI Index](https://publicai.io/model-index/badge?model=winnow-12b-q8)](https://publicai.io/model-index/m/winnow-12b-q8)