← GLM 5.3

Novita · fp8

Serving GLM 5.3. Checked Nov 11.

Matches

Same answer as the maker

typical for the others
75%
76 of 102 prompts
71%
typical for the others
Z.AI · fp8makersame answer twice 62% of the time
Novita · fp875%76 of 102 prompts · typical 71%
Makora · fp474%56 of 76 prompts · typical 71%
Decart · fp474%75 of 102 prompts · typical 71%
GMICloud · fp872%73 of 101 prompts · typical 71%
Reka71%72 of 101 prompts · typical 72%
SiliconFlow · fp870%71 of 102 prompts · typical 72%
Wafer · us58%59 of 101 prompts · typical 72%
Wafer · fp456%57 of 102 prompts · typical 72%
Tenstorrent · fp845%9 of 20 prompts · typical 60%

Every provider gets the same short prompts at temperature 0, so settings cannot change the answer. Honest providers still differ a little, which is why we compare with what is typical, not with 100%.

Question by question

106 questions. Each square is one question. Lit means the same answer as Z.ai. Hover or tap a column.

History

one cell per daily check

Listing

declared precision
fp8
price per 1M
$0.63 in · $1.98 out
CheckHowMeasuredExpectedResult
Top answer106 prompts at temperature 0. How often the top answer equals Z.AI's own endpoint, next to how often the other providers do76 of 102 agreeothers agree 71%pass
Answer spread140 sampled answers compared with Z.AI's own endpoint. Very sensitive: it also picks up harmless setup differences, so it is shown for reference onlydistance 0.27for referenceinfo
Word probabilitiesTop token probability at temperature 0, compared with the other providersgap 0.14returnedpass
Pinned routingRequest pinned to this endpoint with fallbacks offserved by this providerserved by this providerpass
Reasoning switchAsked for no reasoning on a one word answercannot be switched offrespectedpass

No reply yet.

Results say whether a provider's answers match the maker's own endpoint. They are not a claim of intent. Quality checks are not running yet.