Model registry

Methods

Ten pretrained models evaluated across the benchmark. Classifier heads are grouped under their shared backbone; the leaderboard retains each evaluated configuration separately.

ModelOrganizationParametersEvaluated configurationsPaperCodeCheckpoint
ChorusTIC
In-Context Learning
GDUT · Huawei Noah’s Ark Lab · Université Paris Cité · MBZUAI · Shantou UniversityNot reported by authors

ChorusTIC.ckpt (step 6000)

Native in-context inference
PaperCodeWeights
Mantis
Representation Learning
Huawei Noah’s Ark Lab · Université Paris Cité8.11M backbone

Mantis-8M

kNN
LR
MLP
NC
RF
ScaledLR
SVM
PaperCodeWeights
MantisV2
Representation Learning
Huawei Noah’s Ark Lab · Université Paris Cité4.19M backbone

MantisV2

LR
RF
ScaledLR
PaperCodeWeights
MOMENT
Representation Learning
Auton Lab, Carnegie Mellon University125M backbone

MOMENT-1-base

kNN
LR
MLP
NC
RF
SVM
PaperCodeWeights
NuTime
Representation Learning
Microsoft Research · Peking University2.4M backbone

checkpoint_bias9.pth

RF
PaperCodeWeights
TabICL
In-Context Learning
Inria · École Normale Supérieure–PSLNot reported for v1.1 checkpoint

tabicl-classifier-v1.1-20250506.ckpt

Native in-context inference
PaperCodeWeights
TabICLv2
In-Context Learning
Inria · École Normale Supérieure–PSLNot reported for v2 checkpoint

tabicl-classifier-v2-20260212.ckpt

Native in-context inference
PaperCodeWeights
TIC-FM
In-Context Learning
GDUT · Huawei Noah’s Ark Lab · Université Paris Cité · MBZUAINot reported by authors

TSEncoder_orion_icl_fullv1.0.pt

Native in-context inference
PaperCodeWeights
TiCT
In-Context Learning
Visa Research47M (TiCT-Large, ResNet)

No standalone checkpoint link found

Native in-context inference
PaperCodeNo standalone checkpoint link found
UniShape
Representation Learning
SCUT · A*STAR · Khalifa University3.1M backbone

unishape_checkpoint_zeroshot.pth

RF
PaperCodeWeights

Parameter counts marked as backbone-only exclude dataset-specific classifier heads. “Not reported” is used when an official source does not publish the full count.