Skip to main content

MapikaJared PalmerDecision matchup

Decider 35B A3B NVFP4vs.Kev 9B

Which model makes better decisions?

Decider 35B A3B NVFP4 does better in independent tests, while Kev 9B is more popular.

Independent tests
Decider 35B A3B NVFP4ahead1 of 1
Kev 9B0 of 1
Jev Decision Index
Popularity
Decider 35B A3B NVFP40
Kev 9Bahead40
out of 100
Weights and access
Decider 35B A3B NVFP4open, local
Kev 9Bopen, local
Size
Decider 35B A3B NVFP435 B
Kev 9Bn/a
Parameters

Pick Decider 35B A3B NVFP4 for

Jev Decision Index

Pick Kev 9B for

more popular

Shared tests

Independent evaluators and leaderboards only, the newest shared snapshot per evaluator. With 95 % ranges a lead counts when they do not overlap; for hit rates, when it holds in a 95 % test. Without any uncertainty figure at most “slightly ahead”.

Jev Decision Index

Decider 35B A3B NVFP4 ahead

Decider 35B A3B NVFP4 is clearly ahead in 15 of 37 subtests and slightly in 10, Kev 9B in 4 clearly and slightly in 3. 5 are level.

Home appliances · Decision Index 0.4.1

Decider 35B A3B NVFP423.9
Kev 9B11.4

88 tasks, as of October 28, 2026

POP909 · Decision Index 0.4.1

Decider 35B A3B NVFP46.7
Kev 9B10.2

2,000 tasks, as of October 28, 2026

BPoMP · Decision Index 0.4.1

Decider 35B A3B NVFP489.1
Kev 9B58.9

5,000 tasks, as of October 28, 2026

Show all 37 subtests
SubtestDecider 35B A3B NVFP4Kev 9BVerdict
Home appliances · Decision Index 0.4.123.911.4Decider 35B A3B NVFP4 ahead
POP909 · Decision Index 0.4.16.710.2Kev 9B ahead
BPoMP · Decision Index 0.4.189.158.9Decider 35B A3B NVFP4 ahead
GSM8K · Decision Index 0.4.141.554.4Kev 9B ahead
cfcolor · Decision Index 0.4.164.953.0Decider 35B A3B NVFP4 ahead
WinoGrande · Decision Index 0.4.188.675.1Decider 35B A3B NVFP4 ahead
HellaSwag · Decision Index 0.4.196.782.7Decider 35B A3B NVFP4 ahead
Habermas · Decision Index 0.4.146.440.0Decider 35B A3B NVFP4 ahead
API-Bank · Decision Index 0.4.156.565.4Kev 9B ahead
SATA-Bench · Decision Index 0.4.134.730.7Decider 35B A3B NVFP4 ahead
New Yorker · Decision Index 0.4.164.056.6Decider 35B A3B NVFP4 ahead
MuSR · Decision Index 0.4.161.856.5Decider 35B A3B NVFP4 ahead
PhishNChips · Decision Index 0.4.166.961.6Decider 35B A3B NVFP4 ahead
Humicroedit · Decision Index 0.4.162.057.3Decider 35B A3B NVFP4 ahead
BBH · Decision Index 0.4.171.366.3Decider 35B A3B NVFP4 ahead
MMLU-Pro · Decision Index 0.4.160.556.5Decider 35B A3B NVFP4 ahead
CLadder · Decision Index 0.4.166.763.5Decider 35B A3B NVFP4 ahead
HoVer · Decision Index 0.4.163.560.7Decider 35B A3B NVFP4 ahead
BFCL · Decision Index 0.4.192.295.2Kev 9B ahead
ACOS · Decision Index 0.4.127.217.0Decider 35B A3B NVFP4 slightly ahead
iSarcasmEval · Decision Index 0.4.154.843.2Decider 35B A3B NVFP4 slightly ahead
CLINC150 · Decision Index 0.4.194.777.1Decider 35B A3B NVFP4 slightly ahead
ContractNLI · Decision Index 0.4.175.065.3Decider 35B A3B NVFP4 slightly ahead
ANLI · Decision Index 0.4.166.058.1Decider 35B A3B NVFP4 slightly ahead
RAGTruth · Decision Index 0.4.163.170.6Kev 9B slightly ahead
BRIGHT · Decision Index 0.4.141.738.2Decider 35B A3B NVFP4 slightly ahead
BANKING77 · Decision Index 0.4.189.883.3Decider 35B A3B NVFP4 slightly ahead
FinEntity · Decision Index 0.4.185.289.7Kev 9B slightly ahead
NLI4CT · Decision Index 0.4.178.575.2Decider 35B A3B NVFP4 slightly ahead
ToolRet · Decision Index 0.4.166.363.8Decider 35B A3B NVFP4 slightly ahead
VAST · Decision Index 0.4.154.556.7Kev 9B slightly ahead
Amazon ESCI · Decision Index 0.4.150.649.1Decider 35B A3B NVFP4 slightly ahead
HLE · Decision Index 0.4.18.811.0level
ChessBench · Decision Index 0.4.110.912.0level
GPQA Diamond · Decision Index 0.4.140.837.8level
CRUXEval · Decision Index 0.4.159.855.4level
When2Call · Decision Index 0.4.159.760.7level

Source · latest October 28, 2026

All data side by side

Decider 35B A3B NVFP4Kev 9B
KindStandaloneAdapter
DeveloperMapikaJared Palmer
StatusOpen sourceOpen source
Releasedn/aSeptember 20, 2026
Weightsopenopen
Runs locallyyesyes
Parameters35 Bn/a
LicenseApache-2.0Apache-2.0 for the adapter and head
Popularity (out of 100)040