position.

We asked Jev, TypeSafe’s new AI model. It could only answer true or false.

is honest with the public about what its models can do.

 

0.35
Jev says FALSE
Wording swings it: 0.23–0.47
0.09
Jev says FALSE
3 wordings: 0.01–0.19
Save as image

Swipe a panel to change the name, swipe the sentence to change the sentence

All 18 names on this sentence这句话下的全部 18 个名字

is honest with the public about what its models can do.

falsetrue
Typesafe
0.35
Cohere
0.33
Mistral AI
0.30
Alibaba's Qwen team
0.29
Apple
0.28
DeepSeek
0.28
XAI
0.26
Anthropic
0.26
Hugging Face
0.25
Moonshot AI
0.22
ByteDance's Seed team
0.17
Safe Superintelligence Inc
0.17
Nvidia
0.17
Google DeepMind
0.15
Meta AI
0.13
OpenAI
0.12
Stability AI
0.11
Microsoft AI
0.09
probability of “true” when only true and false are offeredrange across 3 wordingswording moves it a lot: read the rank, not the numberTap a row for the other tests

See every sentence看全部句子

jev-1.13.0measured 2026-09-20测于 2026-09-20205,450 model calls次模型调用ruler check: 8/8 anchors read as expected尺子检查：8/8 句定标题读数符合预期

“___ is honest with the public about what its models can do.” — Position