Skip to main content

Jared PalmerFastino LabsDecision matchup

Kev 4Bvs.GLiNER2.5-Decide

Which model makes better decisions?

Kev 4B does better in independent tests, while GLiNER2.5-Decide is more popular.

Independent tests
Kev 4Bahead1 of 1
GLiNER2.5-Decide0 of 1
Jev Decision Index
Popularity
Kev 4B23
GLiNER2.5-Decideahead56
out of 100
Weights and access
Kev 4Bopen, local
GLiNER2.5-Decideopen, local
Size
Kev 4Bn/a
GLiNER2.5-Decide0.34 B
Parameters

Pick Kev 4B for

Jev Decision Index

Pick GLiNER2.5-Decide for

more 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

Kev 4B ahead

Kev 4B is clearly ahead in 20 of 37 subtests and slightly in 13, GLiNER2.5-Decide in 2. 2 are level.

Home appliances · Decision Index 0.4.1

Kev 4B14.8
GLiNER2.5-Decide0.0

88 tasks, as of October 28, 2026

SATA-Bench · Decision Index 0.4.1

Kev 4B28.8
GLiNER2.5-Decide0.7

1,650 tasks, as of October 28, 2026

API-Bank · Decision Index 0.4.1

Kev 4B53.3
GLiNER2.5-Decide7.7

508 tasks, as of October 28, 2026

Show all 37 subtests
SubtestKev 4BGLiNER2.5-DecideVerdict
Home appliances · Decision Index 0.4.114.80.0Kev 4B ahead
SATA-Bench · Decision Index 0.4.128.80.7Kev 4B ahead
API-Bank · Decision Index 0.4.153.37.7Kev 4B ahead
MMLU-Pro · Decision Index 0.4.150.716.1Kev 4B ahead
GSM8K · Decision Index 0.4.146.517.3Kev 4B ahead
HellaSwag · Decision Index 0.4.178.932.2Kev 4B ahead
BFCL · Decision Index 0.4.193.146.2Kev 4B ahead
BBH · Decision Index 0.4.162.531.1Kev 4B ahead
When2Call · Decision Index 0.4.166.733.4Kev 4B ahead
GPQA Diamond · Decision Index 0.4.137.821.4Kev 4B ahead
HLE · Decision Index 0.4.110.216.8GLiNER2.5-Decide ahead
New Yorker · Decision Index 0.4.152.332.2Kev 4B ahead
WinoGrande · Decision Index 0.4.170.250.7Kev 4B ahead
CLadder · Decision Index 0.4.163.150.1Kev 4B ahead
MuSR · Decision Index 0.4.156.345.2Kev 4B ahead
CRUXEval · Decision Index 0.4.148.140.2Kev 4B ahead
HoVer · Decision Index 0.4.159.750.7Kev 4B ahead
BPoMP · Decision Index 0.4.165.158.2Kev 4B ahead
PhishNChips · Decision Index 0.4.155.350.0Kev 4B ahead
cfcolor · Decision Index 0.4.157.953.4Kev 4B ahead
Habermas · Decision Index 0.4.142.045.5GLiNER2.5-Decide ahead
Humicroedit · Decision Index 0.4.154.450.6Kev 4B ahead
ACOS · Decision Index 0.4.19.80.0Kev 4B slightly ahead
ContractNLI · Decision Index 0.4.164.421.8Kev 4B slightly ahead
RAGTruth · Decision Index 0.4.167.525.3Kev 4B slightly ahead
BRIGHT · Decision Index 0.4.139.020.1Kev 4B slightly ahead
Amazon ESCI · Decision Index 0.4.139.723.3Kev 4B slightly ahead
ToolRet · Decision Index 0.4.161.038.2Kev 4B slightly ahead
ANLI · Decision Index 0.4.148.130.9Kev 4B slightly ahead
NLI4CT · Decision Index 0.4.174.648.0Kev 4B slightly ahead
VAST · Decision Index 0.4.152.435.3Kev 4B slightly ahead
iSarcasmEval · Decision Index 0.4.146.832.4Kev 4B slightly ahead
FinEntity · Decision Index 0.4.187.166.2Kev 4B slightly ahead
BANKING77 · Decision Index 0.4.182.965.6Kev 4B slightly ahead
CLINC150 · Decision Index 0.4.175.060.4Kev 4B slightly ahead
POP909 · Decision Index 0.4.11.21.7level
ChessBench · Decision Index 0.4.18.98.1level

Source · latest October 28, 2026

All data side by side

Kev 4BGLiNER2.5-Decide
KindAdapterClassifier
DeveloperJared PalmerFastino Labs
StatusOpen sourceOpen source
ReleasedSeptember 20, 2026n/a
Weightsopenopen
Runs locallyyesyes
Parametersn/a0.34 B
LicenseApache-2.0 for the adapter and headApache-2.0
Popularity (out of 100)2356