Skip to main content

MapikaJared PalmerDecision matchup

Decider 4Bvs.Kev 9B

Which model makes better decisions?

Decider 4B and Kev 9B each lead in different tests.

Independent tests
Decider 4B0 of 1
Kev 9B0 of 1
Jev Decision Index
Popularity
Decider 4B43
Kev 9B40
out of 100
Weights and access
Decider 4Bopen, local
Kev 9Bopen, local
Size
Decider 4B4 B
Kev 9Bn/a
Parameters

Pick Decider 4B for

No clear edge

Pick Kev 9B for

No clear edge

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

depends on the subtest

Kev 9B is clearly ahead in 8 of 37 subtests and slightly in 6, Decider 4B in 6 clearly and slightly in 4. 13 are level.

BPoMP · Decision Index 0.4.1

Decider 4B83.4
Kev 9B58.9

5,000 tasks, as of October 28, 2026

GSM8K · Decision Index 0.4.1

Decider 4B40.6
Kev 9B54.4

2,638 tasks, as of October 28, 2026

CRUXEval · Decision Index 0.4.1

Decider 4B43.7
Kev 9B55.4

570 tasks, as of October 28, 2026

Show all 37 subtests
SubtestDecider 4BKev 9BVerdict
BPoMP · Decision Index 0.4.183.458.9Decider 4B ahead
GSM8K · Decision Index 0.4.140.654.4Kev 9B ahead
CRUXEval · Decision Index 0.4.143.755.4Kev 9B ahead
When2Call · Decision Index 0.4.175.960.7Decider 4B ahead
ChessBench · Decision Index 0.4.110.512.0Kev 9B ahead
cfcolor · Decision Index 0.4.160.553.0Decider 4B ahead
HellaSwag · Decision Index 0.4.194.082.7Decider 4B ahead
New Yorker · Decision Index 0.4.162.956.6Decider 4B ahead
MMLU-Pro · Decision Index 0.4.151.756.5Kev 9B ahead
BBH · Decision Index 0.4.160.966.3Kev 9B ahead
BFCL · Decision Index 0.4.188.095.2Kev 9B ahead
HoVer · Decision Index 0.4.156.360.7Kev 9B ahead
WinoGrande · Decision Index 0.4.180.775.1Decider 4B ahead
PhishNChips · Decision Index 0.4.157.861.6Kev 9B ahead
RAGTruth · Decision Index 0.4.152.270.6Kev 9B slightly ahead
BRIGHT · Decision Index 0.4.145.538.2Decider 4B slightly ahead
Amazon ESCI · Decision Index 0.4.142.449.1Kev 9B slightly ahead
ACOS · Decision Index 0.4.119.217.0Decider 4B slightly ahead
CLINC150 · Decision Index 0.4.186.677.1Decider 4B slightly ahead
BANKING77 · Decision Index 0.4.174.783.3Kev 9B slightly ahead
ContractNLI · Decision Index 0.4.172.365.3Decider 4B slightly ahead
VAST · Decision Index 0.4.153.556.7Kev 9B slightly ahead
FinEntity · Decision Index 0.4.186.089.7Kev 9B slightly ahead
ANLI · Decision Index 0.4.156.458.1Kev 9B slightly ahead
Home appliances · Decision Index 0.4.117.111.4level
GPQA Diamond · Decision Index 0.4.141.337.8level
API-Bank · Decision Index 0.4.160.465.4level
HLE · Decision Index 0.4.110.411.0level
MuSR · Decision Index 0.4.153.756.5level
Humicroedit · Decision Index 0.4.159.757.3level
SATA-Bench · Decision Index 0.4.131.630.7level
iSarcasmEval · Decision Index 0.4.142.143.2level
NLI4CT · Decision Index 0.4.173.775.2level
ToolRet · Decision Index 0.4.165.063.8level
POP909 · Decision Index 0.4.110.010.2level
Habermas · Decision Index 0.4.140.640.0level
CLadder · Decision Index 0.4.163.363.5level

Source · latest October 28, 2026

All data side by side

Decider 4BKev 9B
KindStandaloneAdapter
DeveloperMapikaJared Palmer
StatusOpen sourceOpen source
Releasedn/aSeptember 20, 2026
Weightsopenopen
Runs locallyyesyes
Parameters4 Bn/a
LicenseApache-2.0Apache-2.0 for the adapter and head
Popularity (out of 100)4340