Skip to main content

MapikaInterfaze AIDecision matchup

Decider 4Bvs.Lev

Which model makes better decisions?

Decider 4B and Lev each lead in different tests.

Independent tests
Decider 4B0 of 1
Lev0 of 1
Jev Decision Index
Popularity
Decider 4Bahead43
Lev31
out of 100
Weights and access
Decider 4Bopen, local
Levopen, local
Size
Decider 4B4 B
Lev4 B
Parameters

Pick Decider 4B for

more popular

Pick Lev 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

Decider 4B is clearly ahead in 10 of 37 subtests and slightly in 7, Lev in 7 clearly and slightly in 5. 8 are level.

POP909 · Decision Index 0.4.1

Decider 4B10.0
Lev5.4

2,000 tasks, as of October 28, 2026

SATA-Bench · Decision Index 0.4.1

Decider 4B31.6
Lev18.2

1,650 tasks, as of October 28, 2026

When2Call · Decision Index 0.4.1

Decider 4B75.9
Lev52.3

3,652 tasks, as of October 28, 2026

Show all 37 subtests
SubtestDecider 4BLevVerdict
POP909 · Decision Index 0.4.110.05.4Decider 4B ahead
SATA-Bench · Decision Index 0.4.131.618.2Decider 4B ahead
When2Call · Decision Index 0.4.175.952.3Decider 4B ahead
GSM8K · Decision Index 0.4.140.629.2Decider 4B ahead
ChessBench · Decision Index 0.4.110.514.3Lev ahead
API-Bank · Decision Index 0.4.160.479.1Lev ahead
WinoGrande · Decision Index 0.4.180.766.9Decider 4B ahead
New Yorker · Decision Index 0.4.162.954.0Decider 4B ahead
HellaSwag · Decision Index 0.4.194.081.2Decider 4B ahead
CRUXEval · Decision Index 0.4.143.750.3Lev ahead
PhishNChips · Decision Index 0.4.157.850.6Decider 4B ahead
Habermas · Decision Index 0.4.140.646.2Lev ahead
HoVer · Decision Index 0.4.156.363.4Lev ahead
MMLU-Pro · Decision Index 0.4.151.748.7Decider 4B ahead
CLadder · Decision Index 0.4.163.359.7Decider 4B ahead
BPoMP · Decision Index 0.4.183.487.7Lev ahead
BFCL · Decision Index 0.4.188.090.2Lev ahead
RAGTruth · Decision Index 0.4.152.28.3Decider 4B slightly ahead
ACOS · Decision Index 0.4.119.27.1Decider 4B slightly ahead
FinEntity · Decision Index 0.4.186.074.0Decider 4B slightly ahead
BANKING77 · Decision Index 0.4.174.786.8Lev slightly ahead
ANLI · Decision Index 0.4.156.464.5Lev slightly ahead
VAST · Decision Index 0.4.153.548.4Decider 4B slightly ahead
Amazon ESCI · Decision Index 0.4.142.445.9Lev slightly ahead
iSarcasmEval · Decision Index 0.4.142.140.0Decider 4B slightly ahead
ToolRet · Decision Index 0.4.165.062.2Decider 4B slightly ahead
CLINC150 · Decision Index 0.4.186.690.4Lev slightly ahead
BRIGHT · Decision Index 0.4.145.544.0Decider 4B slightly ahead
NLI4CT · Decision Index 0.4.173.776.1Lev slightly ahead
HLE · Decision Index 0.4.110.412.4level
Home appliances · Decision Index 0.4.117.119.3level
cfcolor · Decision Index 0.4.160.562.2level
ContractNLI · Decision Index 0.4.172.370.4level
GPQA Diamond · Decision Index 0.4.141.340.3level
BBH · Decision Index 0.4.160.961.3level
Humicroedit · Decision Index 0.4.159.760.1level
MuSR · Decision Index 0.4.153.753.6level

Source · latest October 28, 2026

All data side by side

Decider 4BLev
KindStandaloneAdapter
DeveloperMapikaInterfaze AI
StatusOpen sourceOpen source
Weightsopenopen
Runs locallyyesyes
Parameters4 B4 B
LicenseApache-2.0Apache-2.0
Popularity (out of 100)4331