Request a pilot

‹ PublicAI Index

The LLM benchmark aggregator.

Certo v1

Other

Strongest in Calibration (#7 of 85), weakest in Routing & classification (#85 of 85). Above par in 1 of 3 scopes. Among the models it meets almost everywhere, it finishes behind DeepSeek V4.1 Flash and GPT-6 Luna and ahead of OpenDecision and Alibaba GTE Reranker ModernBERT-base.

§ 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.

Decisions45.1−28.2#61/851/1

Calibration64.3−8.4#7/851/1

Routing & classification26−48#85/851/1

§ 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 Certo v1, left for the other.

Mirrorwon 2 · lost 1

Raw Qwen3 0.6B direct logitswon 2 · lost 1

GLiNER2won 2 · lost 1

GLiNER2 largewon 2 · lost 1

Raw Qwen3 1.7B direct logitswon 2 · lost 1

CLM 8Bwon 2 · lost 1

SimpleJevwon 2 · lost 1

GLiNER2.5 smallwon 2 · lost 1

Raw Qwen3 8B direct logitswon 2 · lost 1

Open Jev JSON Canvaswon 2 · lost 1

openJev Verdictwon 2 · lost 1

Raw Qwen3 4B Instruct direct logitswon 2 · lost 1

System Onewon 2 · lost 1

GLiNER2.5 multiwon 2 · lost 1

kev 0.5Bwon 2 · lost 1

Decider 2Bwon 2 · lost 1

kev 4Bwon 2 · lost 1

kev 8Bwon 2 · lost 1

Verdict Smallwon 2 · lost 1

JevActwon 2 · lost 1

Smalljev semantic-v9won 2 · lost 1

kev 0.6Bwon 2 · lost 1

Alibaba GTE Reranker ModernBERT-basewon 2 · lost 1

OpenDecisionwon 2 · lost 1

Laya 322Mwon 1 · lost 1

Open Jev Deberta V3 Largewon 1 · lost 2

Spark S1 4B V6won 1 · lost 2

Malkuth 2Bwon 1 · lost 2

Qwen3.5-0.8B Decision Modelwon 1 · lost 2

Typecastlmwon 1 · lost 2

Open Alternative Jevwon 1 · lost 2

Open-Jev 2Bwon 1 · lost 2

Layawon 1 · lost 2

System One Openwon 1 · lost 2

openJev Verdict 1.4won 1 · lost 2

Raw Phi-4 mini direct logitswon 1 · lost 2

Decision Fastwon 1 · lost 2

OpenSourceJevwon 1 · lost 2

Bespoke Nimble 9Bwon 1 · lost 2

Jeffwon 1 · lost 2

Malkuth 4Bwon 1 · lost 2

Lev 350Mwon 1 · lost 2

SimpleJev Qwen3.6-35B-A3Bwon 1 · lost 2

Open-Jev 9Bwon 1 · lost 2

Qwen3.5-9B Jev-like data-mix v2won 1 · lost 2

Vonwon 1 · lost 2

Decision Machine 1won 1 · lost 2

Jev Localwon 1 · lost 2

Qwen3 Reranker 4Bwon 1 · lost 2

Jobe Qwen3.5-4Bwon 1 · lost 2

Jev Omniwon 1 · lost 2

SemIfwon 1 · lost 2

Metask Jev 4Bwon 1 · lost 2

Standard One 8Bwon 1 · lost 2

Decision 2Bwon 1 · lost 2

Decider 35B A3Bwon 1 · lost 2

Winnow-12B Q8won 1 · lost 2

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

Openjev Sglangwon 1 · lost 2

LitJevwon 1 · lost 2

Reflex 27Bwon 1 · lost 2

JevK5 v0.2.0won 1 · lost 2

swanOnewon 1 · lost 2

Decider-4b v2won 1 · lost 2

Cygnetwon 1 · lost 2

JevOnewon 1 · lost 2

SimpleJev Qwen3.8-27Bwon 1 · lost 2

Hopperwon 1 · lost 2

NInfer Qwen3.8-27B NVFP4won 1 · lost 2

NInfer Qwen3.8-Flash-Next mixedwon 1 · lost 2

Jev 1.13.0won 1 · lost 2

Instinctwon 1 · lost 2

Gemma 4 31B IT (Autoloops)won 1 · lost 2

Djev Sparkwon 0 · lost 2

Gemma 4 31Bwon 0 · lost 2

Mixedbread mxbai-rerank-base-v2won 0 · lost 3

BAAI bge-reranker-v2-m3won 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 0.1%JevBench · Calibration 83%

Badge

PublicAI Index badge for Certo v1

[![PublicAI Index](https://publicai.io/model-index/badge?model=certo-v1)](https://publicai.io/model-index/m/certo-v1)