Skip to main content

MapikaFastino LabsDecision matchup

Decider 4Bvs.GLiNER2.5-Decide

Which model makes better decisions?

Decider 4B does better in independent tests, while GLiNER2.5-Decide is much smaller.

Independent tests
Decider 4Bahead1 of 1
GLiNER2.5-Decide0 of 1
Jev Decision Index
Popularity
Decider 4B43
GLiNER2.5-Decideahead56
out of 100
Weights and access
Decider 4Bopen, local
GLiNER2.5-Decideopen, local
Size
Decider 4B4 B
GLiNER2.5-Decidesmaller0.34 B
Parameters

Pick Decider 4B for

Jev Decision Index

Pick GLiNER2.5-Decide for

smallermore 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 4B ahead

Decider 4B is clearly ahead in 21 of 37 subtests and slightly in 13, GLiNER2.5-Decide in 2. 1 is level.

Home appliances · Decision Index 0.4.1

Decider 4B17.1
GLiNER2.5-Decide0.0

88 tasks, as of October 28, 2026

SATA-Bench · Decision Index 0.4.1

Decider 4B31.6
GLiNER2.5-Decide0.7

1,650 tasks, as of October 28, 2026

API-Bank · Decision Index 0.4.1

Decider 4B60.4
GLiNER2.5-Decide7.7

508 tasks, as of October 28, 2026

Show all 37 subtests
SubtestDecider 4BGLiNER2.5-DecideVerdict
Home appliances · Decision Index 0.4.117.10.0Decider 4B ahead
SATA-Bench · Decision Index 0.4.131.60.7Decider 4B ahead
API-Bank · Decision Index 0.4.160.47.7Decider 4B ahead
POP909 · Decision Index 0.4.110.01.7Decider 4B ahead
MMLU-Pro · Decision Index 0.4.151.716.1Decider 4B ahead
HellaSwag · Decision Index 0.4.194.032.2Decider 4B ahead
GSM8K · Decision Index 0.4.140.617.3Decider 4B ahead
When2Call · Decision Index 0.4.175.933.4Decider 4B ahead
BBH · Decision Index 0.4.160.931.1Decider 4B ahead
New Yorker · Decision Index 0.4.162.932.2Decider 4B ahead
GPQA Diamond · Decision Index 0.4.141.321.4Decider 4B ahead
BFCL · Decision Index 0.4.188.046.2Decider 4B ahead
HLE · Decision Index 0.4.110.416.8GLiNER2.5-Decide ahead
WinoGrande · Decision Index 0.4.180.750.7Decider 4B ahead
BPoMP · Decision Index 0.4.183.458.2Decider 4B ahead
ChessBench · Decision Index 0.4.110.58.1Decider 4B ahead
CLadder · Decision Index 0.4.163.350.1Decider 4B ahead
MuSR · Decision Index 0.4.153.745.2Decider 4B ahead
Humicroedit · Decision Index 0.4.159.750.6Decider 4B ahead
PhishNChips · Decision Index 0.4.157.850.0Decider 4B ahead
cfcolor · Decision Index 0.4.160.553.4Decider 4B ahead
Habermas · Decision Index 0.4.140.645.5GLiNER2.5-Decide ahead
HoVer · Decision Index 0.4.156.350.7Decider 4B ahead
ACOS · Decision Index 0.4.119.20.0Decider 4B slightly ahead
ContractNLI · Decision Index 0.4.172.321.8Decider 4B slightly ahead
BRIGHT · Decision Index 0.4.145.520.1Decider 4B slightly ahead
RAGTruth · Decision Index 0.4.152.225.3Decider 4B slightly ahead
ANLI · Decision Index 0.4.156.430.9Decider 4B slightly ahead
Amazon ESCI · Decision Index 0.4.142.423.3Decider 4B slightly ahead
ToolRet · Decision Index 0.4.165.038.2Decider 4B slightly ahead
NLI4CT · Decision Index 0.4.173.748.0Decider 4B slightly ahead
VAST · Decision Index 0.4.153.535.3Decider 4B slightly ahead
CLINC150 · Decision Index 0.4.186.660.4Decider 4B slightly ahead
FinEntity · Decision Index 0.4.186.066.2Decider 4B slightly ahead
iSarcasmEval · Decision Index 0.4.142.132.4Decider 4B slightly ahead
BANKING77 · Decision Index 0.4.174.765.6Decider 4B slightly ahead
CRUXEval · Decision Index 0.4.143.740.2level

Source · latest October 28, 2026

All data side by side

Decider 4BGLiNER2.5-Decide
KindStandaloneClassifier
DeveloperMapikaFastino Labs
StatusOpen sourceOpen source
Weightsopenopen
Runs locallyyesyes
Parameters4 B0.34 B
LicenseApache-2.0Apache-2.0
Popularity (out of 100)4356