Skip to main content

MapikaJared PalmerDecision matchup

Decider 4Bvs.Kev 4B

Which model makes better decisions?

Decider 4B does better in independent tests.

Independent tests
Decider 4Bahead1 of 1
Kev 4B0 of 1
Jev Decision Index
Popularity
Decider 4Bahead43
Kev 4B23
out of 100
Weights and access
Decider 4Bopen, local
Kev 4Bopen, local
Size
Decider 4B4 B
Kev 4Bn/a
Parameters

Pick Decider 4B for

Jev Decision Indexmore popular

Pick Kev 4B 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

Decider 4B ahead

Decider 4B is clearly ahead in 10 of 37 subtests and slightly in 7, Kev 4B in 3 clearly and slightly in 3. 14 are level.

POP909 · Decision Index 0.4.1

Decider 4B10.0
Kev 4B1.2

2,000 tasks, as of October 28, 2026

BPoMP · Decision Index 0.4.1

Decider 4B83.4
Kev 4B65.1

5,000 tasks, as of October 28, 2026

New Yorker · Decision Index 0.4.1

Decider 4B62.9
Kev 4B52.3

528 tasks, as of October 28, 2026

Show all 37 subtests
SubtestDecider 4BKev 4BVerdict
POP909 · Decision Index 0.4.110.01.2Decider 4B ahead
BPoMP · Decision Index 0.4.183.465.1Decider 4B ahead
New Yorker · Decision Index 0.4.162.952.3Decider 4B ahead
HellaSwag · Decision Index 0.4.194.078.9Decider 4B ahead
ChessBench · Decision Index 0.4.110.58.9Decider 4B ahead
WinoGrande · Decision Index 0.4.180.770.2Decider 4B ahead
GSM8K · Decision Index 0.4.140.646.5Kev 4B ahead
When2Call · Decision Index 0.4.175.966.7Decider 4B ahead
API-Bank · Decision Index 0.4.160.453.3Decider 4B ahead
Humicroedit · Decision Index 0.4.159.754.4Decider 4B ahead
HoVer · Decision Index 0.4.156.359.7Kev 4B ahead
BFCL · Decision Index 0.4.188.093.1Kev 4B ahead
cfcolor · Decision Index 0.4.160.557.9Decider 4B ahead
ACOS · Decision Index 0.4.119.29.8Decider 4B slightly ahead
RAGTruth · Decision Index 0.4.152.267.5Kev 4B slightly ahead
ANLI · Decision Index 0.4.156.448.1Decider 4B slightly ahead
BRIGHT · Decision Index 0.4.145.539.0Decider 4B slightly ahead
CLINC150 · Decision Index 0.4.186.675.0Decider 4B slightly ahead
ContractNLI · Decision Index 0.4.172.364.4Decider 4B slightly ahead
iSarcasmEval · Decision Index 0.4.142.146.8Kev 4B slightly ahead
BANKING77 · Decision Index 0.4.174.782.9Kev 4B slightly ahead
Amazon ESCI · Decision Index 0.4.142.439.7Decider 4B slightly ahead
ToolRet · Decision Index 0.4.165.061.0Decider 4B slightly ahead
Home appliances · Decision Index 0.4.117.114.8level
CRUXEval · Decision Index 0.4.143.748.1level
SATA-Bench · Decision Index 0.4.131.628.8level
GPQA Diamond · Decision Index 0.4.141.337.8level
MuSR · Decision Index 0.4.153.756.3level
PhishNChips · Decision Index 0.4.157.855.3level
Habermas · Decision Index 0.4.140.642.0level
BBH · Decision Index 0.4.160.962.5level
VAST · Decision Index 0.4.153.552.4level
HLE · Decision Index 0.4.110.410.2level
MMLU-Pro · Decision Index 0.4.151.750.7level
FinEntity · Decision Index 0.4.186.087.1level
NLI4CT · Decision Index 0.4.173.774.6level
CLadder · Decision Index 0.4.163.363.1level

Source · latest October 28, 2026

All data side by side

Decider 4BKev 4B
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)4323