Skip to main content

MapikaDecision matchup

Decider 4Bvs.Decider 35B A3B NVFP4

Which model makes better decisions?

Decider 35B A3B NVFP4 does better in independent tests, while Decider 4B is much smaller.

Independent tests
Decider 4B0 of 1
Decider 35B A3B NVFP4ahead1 of 1
Jev Decision Index
Popularity
Decider 4Bahead43
Decider 35B A3B NVFP40
out of 100
Weights and access
Decider 4Bopen, local
Decider 35B A3B NVFP4open, local
Size
Decider 4Bsmaller4 B
Decider 35B A3B NVFP435 B
Parameters

Pick Decider 4B for

smallermore popular

Pick Decider 35B A3B NVFP4 for

Jev Decision Index

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 13 of 37 subtests and slightly in 9, Decider 4B in 2 clearly and slightly in 1. 12 are level.

POP909 · Decision Index 0.4.1

Decider 4B10.0
Decider 35B A3B NVFP46.7

2,000 tasks, as of October 28, 2026

CRUXEval · Decision Index 0.4.1

Decider 4B43.7
Decider 35B A3B NVFP459.8

570 tasks, as of October 28, 2026

When2Call · Decision Index 0.4.1

Decider 4B75.9
Decider 35B A3B NVFP459.7

3,652 tasks, as of October 28, 2026

Show all 37 subtests
SubtestDecider 4BDecider 35B A3B NVFP4Verdict
POP909 · Decision Index 0.4.110.06.7Decider 4B ahead
CRUXEval · Decision Index 0.4.143.759.8Decider 35B A3B NVFP4 ahead
When2Call · Decision Index 0.4.175.959.7Decider 4B ahead
BBH · Decision Index 0.4.160.971.3Decider 35B A3B NVFP4 ahead
MMLU-Pro · Decision Index 0.4.151.760.5Decider 35B A3B NVFP4 ahead
PhishNChips · Decision Index 0.4.157.866.9Decider 35B A3B NVFP4 ahead
MuSR · Decision Index 0.4.153.761.8Decider 35B A3B NVFP4 ahead
Habermas · Decision Index 0.4.140.646.4Decider 35B A3B NVFP4 ahead
HoVer · Decision Index 0.4.156.363.5Decider 35B A3B NVFP4 ahead
WinoGrande · Decision Index 0.4.180.788.6Decider 35B A3B NVFP4 ahead
cfcolor · Decision Index 0.4.160.564.9Decider 35B A3B NVFP4 ahead
BPoMP · Decision Index 0.4.183.489.1Decider 35B A3B NVFP4 ahead
CLadder · Decision Index 0.4.163.366.7Decider 35B A3B NVFP4 ahead
BFCL · Decision Index 0.4.188.092.2Decider 35B A3B NVFP4 ahead
HellaSwag · Decision Index 0.4.194.096.7Decider 35B A3B NVFP4 ahead
ACOS · Decision Index 0.4.119.227.2Decider 35B A3B NVFP4 slightly ahead
iSarcasmEval · Decision Index 0.4.142.154.8Decider 35B A3B NVFP4 slightly ahead
RAGTruth · Decision Index 0.4.152.263.1Decider 35B A3B NVFP4 slightly ahead
BANKING77 · Decision Index 0.4.174.789.8Decider 35B A3B NVFP4 slightly ahead
Amazon ESCI · Decision Index 0.4.142.450.6Decider 35B A3B NVFP4 slightly ahead
ANLI · Decision Index 0.4.156.466.0Decider 35B A3B NVFP4 slightly ahead
CLINC150 · Decision Index 0.4.186.694.7Decider 35B A3B NVFP4 slightly ahead
BRIGHT · Decision Index 0.4.145.541.7Decider 4B slightly ahead
NLI4CT · Decision Index 0.4.173.778.5Decider 35B A3B NVFP4 slightly ahead
ContractNLI · Decision Index 0.4.172.375.0Decider 35B A3B NVFP4 slightly ahead
Home appliances · Decision Index 0.4.117.123.9level
HLE · Decision Index 0.4.110.48.8level
SATA-Bench · Decision Index 0.4.131.634.7level
API-Bank · Decision Index 0.4.160.456.5level
Humicroedit · Decision Index 0.4.159.762.0level
ChessBench · Decision Index 0.4.110.510.9level
GSM8K · Decision Index 0.4.140.641.5level
ToolRet · Decision Index 0.4.165.066.3level
VAST · Decision Index 0.4.153.554.5level
New Yorker · Decision Index 0.4.162.964.0level
GPQA Diamond · Decision Index 0.4.141.340.8level
FinEntity · Decision Index 0.4.186.085.2level

Source · latest October 28, 2026

All data side by side

Decider 4BDecider 35B A3B NVFP4
KindStandaloneStandalone
DeveloperMapikaMapika
StatusOpen sourceOpen source
Weightsopenopen
Runs locallyyesyes
Parameters4 B35 B
LicenseApache-2.0Apache-2.0
Popularity (out of 100)430