Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Mirror

Other

Strongest in Calibration (#79 of 85), weakest in Decisions (#85 of 85). Above par in 0 of 3 scopes. Among the models it meets almost everywhere, it finishes behind DeepSeek V4.1 Flash and GPT-6 Luna.

§ 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.

Decisions27.8#85/85
Calibration26#79/85
Routing & classification29.7#81/85

§ 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 Mirror, left for the other.

Raw Qwen3 0.6B direct logitswon 1 · lost 2
GLiNER2won 1 · lost 2
GLiNER2 largewon 1 · lost 2
Raw Qwen3 1.7B direct logitswon 1 · lost 2
Raw Qwen3 8B direct logitswon 1 · lost 2
Open Jev JSON Canvaswon 1 · lost 2
Alibaba GTE Reranker ModernBERT-basewon 1 · lost 2
Certo v1won 1 · lost 2
Mixedbread mxbai-rerank-base-v2won 1 · lost 2
BAAI bge-reranker-v2-m3won 1 · lost 2
Laya 322Mwon 0 · lost 2
Djev Sparkwon 0 · lost 2
Gemma 4 31Bwon 0 · lost 2
CLM 8Bwon 0 · lost 3
SimpleJevwon 0 · lost 3
GLiNER2.5 smallwon 0 · lost 3
openJev Verdictwon 0 · lost 3
Raw Qwen3 4B Instruct direct logitswon 0 · lost 3
System Onewon 0 · lost 3
GLiNER2.5 multiwon 0 · lost 3
kev 0.5Bwon 0 · lost 3
Decider 2Bwon 0 · lost 3
kev 4Bwon 0 · lost 3
kev 8Bwon 0 · lost 3
Verdict Smallwon 0 · lost 3
JevActwon 0 · lost 3
Smalljev semantic-v9won 0 · lost 3
kev 0.6Bwon 0 · lost 3
OpenDecisionwon 0 · lost 3
Open Jev Deberta V3 Largewon 0 · lost 3
Spark S1 4B V6won 0 · lost 3
Malkuth 2Bwon 0 · lost 3
Qwen3.5-0.8B Decision Modelwon 0 · lost 3
Typecastlmwon 0 · lost 3
Open Alternative Jevwon 0 · lost 3
Open-Jev 2Bwon 0 · lost 3
Layawon 0 · lost 3
System One Openwon 0 · lost 3
openJev Verdict 1.4won 0 · lost 3
Raw Phi-4 mini direct logitswon 0 · lost 3
Decision Fastwon 0 · lost 3
OpenSourceJevwon 0 · lost 3
Bespoke Nimble 9Bwon 0 · lost 3
Jeffwon 0 · lost 3
Malkuth 4Bwon 0 · lost 3
Lev 350Mwon 0 · lost 3
SimpleJev Qwen3.6-35B-A3Bwon 0 · lost 3
Open-Jev 9Bwon 0 · lost 3
Qwen3.5-9B Jev-like data-mix v2won 0 · lost 3
Vonwon 0 · lost 3
Decision Machine 1won 0 · lost 3
Jev Localwon 0 · lost 3
Qwen3 Reranker 4Bwon 0 · lost 3
Jobe Qwen3.5-4Bwon 0 · lost 3
Jev Omniwon 0 · lost 3
SemIfwon 0 · lost 3
Metask Jev 4Bwon 0 · lost 3
Standard One 8Bwon 0 · lost 3
Decision 2Bwon 0 · lost 3
Decider 35B A3Bwon 0 · lost 3
Winnow-12B Q8won 0 · lost 3
JEV Qwen3.5-9B Base NVFP4won 0 · lost 3
Gemini 3.1 Flash Litewon 0 · lost 3
OpenJevwon 0 · lost 3
ZeroEntropy zerank-2won 0 · lost 3
local-jev Qwen3.5-4Bwon 0 · lost 3
Jqvwon 0 · lost 3
reflex 4Bwon 0 · lost 3
Openjev Sglangwon 0 · lost 3
LitJevwon 0 · lost 3
Reflex 27Bwon 0 · lost 3
JevK5 v0.2.0won 0 · lost 3
swanOnewon 0 · lost 3
Decider-4b v2won 0 · lost 3
Cygnetwon 0 · lost 3
JevOnewon 0 · lost 3
SimpleJev Qwen3.8-27Bwon 0 · lost 3
Hopperwon 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 13.6%JevBench · Calibration 26%

Badge

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