Skip to main content

Contrastive-LMFastino LabsDecision matchup

CLM-v0.1-8Bvs.GLiNER2.5-Decide

Which model makes better decisions?

CLM-v0.1-8B and GLiNER2.5-Decide each lead in different tests.

Independent tests
CLM-v0.1-8B0 of 1
GLiNER2.5-Decide0 of 1
Jev Decision Index
Popularity
CLM-v0.1-8B37
GLiNER2.5-Decideahead56
out of 100
Weights and access
CLM-v0.1-8Bopen, local
GLiNER2.5-Decideopen, local
Size
CLM-v0.1-8B8 B
GLiNER2.5-Decidesmaller0.34 B
Parameters

Pick CLM-v0.1-8B for

No clear edge

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

depends on the subtest

GLiNER2.5-Decide is clearly ahead in 8 of 37 subtests and slightly in 7, CLM-v0.1-8B in 6 clearly and slightly in 5. 11 are level.

POP909 · Decision Index 0.4.1

CLM-v0.1-8B0.0
GLiNER2.5-Decide1.7

2,000 tasks, as of October 28, 2026

SATA-Bench · Decision Index 0.4.1

CLM-v0.1-8B5.6
GLiNER2.5-Decide0.7

1,650 tasks, as of October 28, 2026

BPoMP · Decision Index 0.4.1

CLM-v0.1-8B32.9
GLiNER2.5-Decide58.2

5,000 tasks, as of October 28, 2026

Show all 37 subtests
SubtestCLM-v0.1-8BGLiNER2.5-DecideVerdict
POP909 · Decision Index 0.4.10.01.7GLiNER2.5-Decide ahead
SATA-Bench · Decision Index 0.4.15.60.7CLM-v0.1-8B ahead
BPoMP · Decision Index 0.4.132.958.2GLiNER2.5-Decide ahead
MuSR · Decision Index 0.4.134.645.2GLiNER2.5-Decide ahead
PhishNChips · Decision Index 0.4.165.150.0CLM-v0.1-8B ahead
New Yorker · Decision Index 0.4.125.432.2GLiNER2.5-Decide ahead
HellaSwag · Decision Index 0.4.140.432.2CLM-v0.1-8B ahead
Habermas · Decision Index 0.4.137.145.5GLiNER2.5-Decide ahead
BFCL · Decision Index 0.4.138.946.2GLiNER2.5-Decide ahead
When2Call · Decision Index 0.4.138.733.4CLM-v0.1-8B ahead
MMLU-Pro · Decision Index 0.4.114.716.1GLiNER2.5-Decide ahead
Humicroedit · Decision Index 0.4.155.650.6CLM-v0.1-8B ahead
CLadder · Decision Index 0.4.153.950.1CLM-v0.1-8B ahead
cfcolor · Decision Index 0.4.150.853.4GLiNER2.5-Decide ahead
ACOS · Decision Index 0.4.13.10.0CLM-v0.1-8B slightly ahead
BANKING77 · Decision Index 0.4.16.565.6GLiNER2.5-Decide slightly ahead
CLINC150 · Decision Index 0.4.18.960.4GLiNER2.5-Decide slightly ahead
Amazon ESCI · Decision Index 0.4.15.023.3GLiNER2.5-Decide slightly ahead
RAGTruth · Decision Index 0.4.151.825.3CLM-v0.1-8B slightly ahead
FinEntity · Decision Index 0.4.133.466.2GLiNER2.5-Decide slightly ahead
VAST · Decision Index 0.4.122.735.3GLiNER2.5-Decide slightly ahead
BRIGHT · Decision Index 0.4.129.220.1CLM-v0.1-8B slightly ahead
NLI4CT · Decision Index 0.4.156.548.0CLM-v0.1-8B slightly ahead
ContractNLI · Decision Index 0.4.120.121.8GLiNER2.5-Decide slightly ahead
ToolRet · Decision Index 0.4.140.338.2CLM-v0.1-8B slightly ahead
iSarcasmEval · Decision Index 0.4.131.232.4GLiNER2.5-Decide slightly ahead
API-Bank · Decision Index 0.4.16.17.7level
CRUXEval · Decision Index 0.4.142.840.2level
HLE · Decision Index 0.4.115.816.8level
GPQA Diamond · Decision Index 0.4.120.421.4level
HoVer · Decision Index 0.4.152.050.7level
ANLI · Decision Index 0.4.131.630.9level
ChessBench · Decision Index 0.4.18.28.1level
BBH · Decision Index 0.4.130.831.1level
GSM8K · Decision Index 0.4.117.517.3level
WinoGrande · Decision Index 0.4.150.850.7level
Home appliances · Decision Index 0.4.10.00.0level

Source · latest October 28, 2026

All data side by side

CLM-v0.1-8BGLiNER2.5-Decide
KindStandaloneClassifier
DeveloperContrastive-LMFastino Labs
StatusOpen weightsOpen source
Weightsopenopen
Runs locallyyesyes
Parameters8 B0.34 B
LicenseApache-2.0Apache-2.0
Popularity (out of 100)3756