Model profile

RealTabPFN 2.5

TabPFN 2.5, by Prior Labs, uses a pretrained transformer to make predictions from labelled examples, extending the v2 family to wider tables. Its default classifier includes pretraining on real datasets, while its default regressor is pretrained on synthetic data only.

Tabular FoundationRegular feature limit: 2,000Source ↗

Model profile

RealTabPFN 2.5

Default parameters. Peer models use their prespecified benchmark-default configuration without per-dataset tuning. This card describes that configuration, not the best achievable tuned model.

Operating map

Macro-F1 Elo relative to Random Forest. Columns are training-sample caps; rows are dataset modalities. Small labels show the number of binding targets.

Elo difference vs. Random Forest

Fixed nonlinear scale; extremes capped at ±1,000 Elo.

No result / comparison unavailable

Reliability

Failure rate map

Dataset modality

Failed fits / (successful + failed fits) for the selected model and modality. Design skips are omitted. A dash means no attempted fits; 0% means all attempted fits succeeded. Hover for counts. Colours span 0–20%, with rates above 20% using the darkest shade; cell labels and hover retain the actual rate. This chart is independent of the performance sensitivity view.

Reference benchmark results

Strict Macro-F1 Elo at p=10,000, n=100. Random Forest is anchored at 1,000; intervals are target-bootstrap 95% intervals. These reference results stay fixed while you explore other budgets in the charts. Overlapping intervals do not establish a clear winner.

Dataset modality	Elo	95% interval	Targets
All modalities	1,159	1,107–1,208	44
DNA methylation	1,203	1,063–1,476	4
GLM/PLM Embeddings	1,218	1,099–1,419	4
Gene expression	1,249	1,072–1,407	10
Genomic prediction	903	812–955	4
Metagenomics	1,161	1,098–1,231	10
Molecular properties	1,145	1,062–1,236	10
Other	1,299	1,293–1,387	2