Skip to main content

Contrastive-LMSupersonic LabsDecision matchup

CLM-v0.1-8Bvs.Julia 1

Which model makes better decisions?

CLM-v0.1-8B and Julia 1 each lead in different tests.

Independent tests
CLM-v0.1-8B0 of 1
Julia 10 of 1
Jev Decision Index
Popularity
CLM-v0.1-8B37
Julia 139
out of 100
Weights and access
CLM-v0.1-8Bopen, local
Julia 1open, local
Size
CLM-v0.1-8B8 B
Julia 1smaller0.14 B
Parameters

Pick CLM-v0.1-8B for

No clear edge

Pick Julia 1 for

smaller

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

CLM-v0.1-8B is clearly ahead in 6 of 37 subtests and slightly in 5, Julia 1 in 4 clearly and slightly in 5. 17 are level.

POP909 · Decision Index 0.4.1

CLM-v0.1-8B0.0
Julia 10.2

2,000 tasks, as of October 28, 2026

SATA-Bench · Decision Index 0.4.1

CLM-v0.1-8B5.6
Julia 11.0

1,650 tasks, as of October 28, 2026

API-Bank · Decision Index 0.4.1

CLM-v0.1-8B6.1
Julia 118.3

508 tasks, as of October 28, 2026

Show all 37 subtests
SubtestCLM-v0.1-8BJulia 1Verdict
POP909 · Decision Index 0.4.10.00.2Julia 1 ahead
SATA-Bench · Decision Index 0.4.15.61.0CLM-v0.1-8B ahead
API-Bank · Decision Index 0.4.16.118.3Julia 1 ahead
When2Call · Decision Index 0.4.138.723.6CLM-v0.1-8B ahead
BPoMP · Decision Index 0.4.132.948.8Julia 1 ahead
HellaSwag · Decision Index 0.4.140.429.9CLM-v0.1-8B ahead
PhishNChips · Decision Index 0.4.165.149.9CLM-v0.1-8B ahead
Humicroedit · Decision Index 0.4.155.648.3CLM-v0.1-8B ahead
BBH · Decision Index 0.4.130.833.8Julia 1 ahead
CLadder · Decision Index 0.4.153.950.2CLM-v0.1-8B ahead
BANKING77 · Decision Index 0.4.16.542.6Julia 1 slightly ahead
iSarcasmEval · Decision Index 0.4.131.26.5CLM-v0.1-8B slightly ahead
Amazon ESCI · Decision Index 0.4.15.020.6Julia 1 slightly ahead
BRIGHT · Decision Index 0.4.129.29.1CLM-v0.1-8B slightly ahead
ToolRet · Decision Index 0.4.140.313.6CLM-v0.1-8B slightly ahead
ContractNLI · Decision Index 0.4.120.131.8Julia 1 slightly ahead
VAST · Decision Index 0.4.122.732.9Julia 1 slightly ahead
CLINC150 · Decision Index 0.4.18.912.3Julia 1 slightly ahead
NLI4CT · Decision Index 0.4.156.549.7CLM-v0.1-8B slightly ahead
ANLI · Decision Index 0.4.131.628.6CLM-v0.1-8B slightly ahead
GPQA Diamond · Decision Index 0.4.120.425.5level
MuSR · Decision Index 0.4.134.639.0level
CRUXEval · Decision Index 0.4.142.838.1level
HLE · Decision Index 0.4.115.814.4level
ChessBench · Decision Index 0.4.18.27.5level
New Yorker · Decision Index 0.4.125.423.5level
Habermas · Decision Index 0.4.137.135.4level
BFCL · Decision Index 0.4.138.937.5level
GSM8K · Decision Index 0.4.117.516.9level
HoVer · Decision Index 0.4.152.050.3level
FinEntity · Decision Index 0.4.133.432.8level
cfcolor · Decision Index 0.4.150.850.4level
ACOS · Decision Index 0.4.13.13.1level
RAGTruth · Decision Index 0.4.151.852.0level
WinoGrande · Decision Index 0.4.150.850.7level
MMLU-Pro · Decision Index 0.4.114.714.7level
Home appliances · Decision Index 0.4.10.00.0level

Source · latest October 28, 2026

All data side by side

CLM-v0.1-8BJulia 1
KindStandaloneClassifier
DeveloperContrastive-LMSupersonic Labs
StatusOpen weightsOpen source
Weightsopenopen
Runs locallyyesyes
Parameters8 B0.14 B
LicenseApache-2.0Apache-2.0
Popularity (out of 100)3739