TiRex vs Laplace
TiRex is a 35M-parameter, xLSTM-based zero-shot forecaster that emits quantile predictions directly. Loaded from NX-AI/TiRex on CPU. Commercial use is gated above €100M revenue; included here under research use with the required attribution.
Resources: GitHub · Model card · Paper (arXiv 2505.23719) · License
Live snapshot Derived from the week-long round-robin study; counts grow as coverage deepens. Everything scores against Laplace on the identical series and windows.
Standalone
The model's own predictive, run zero-shot, scored per series against Laplace by a one-step-ahead (k=1) Diebold–Mariano test on the log-score differential.
| stratum | n | win / draw / loss vs Laplace | med ΔLL | CRPS ratio | cov₀₀ |
|---|---|---|---|---|---|
| economic change-series, business-daily | 1328 | -0.85 | 1.006 | 0.84 | |
| economic change-series, weekly | 2720 | -1.03 | 0.950 | 0.82 | |
| economic change-series, monthly (annual cycle) | 2720 | -0.81 | 0.937 | 0.80 | |
| M4 hourly, strongly seasonal | 414 | -0.88 | 0.986 | 0.76 | |
| asset prices and returns, daily | 1392 | -0.58 | 1.023 | 0.82 |
Median per-series Δ log-likelihood in nats (negative is worse than Laplace); CRPS ratio to Laplace (above 1 is worse); raw central-90% coverage (0.90 target).
Star plot
TiRex standalone against Laplace, on the same six regime axes as the site's
standalone radar. Each radius is the log-likelihood
ratio, (wins + ½·ties) / n scaled so an even split with
Laplace sits on the dashed 1.0 ring; outward beats Laplace more often, inward less. The
M4-hourly set splits into soft and hard waveforms by corpus order, matching that radar.
Collaborative use
Two collaborative arms wrap TiRex's own predictive. @lap
lets Laplace forecast the model's normal scores, which fixes coverage; &lap
holds Laplace and that wrap in a long-only online portfolio, so the blend is never
much worse than Laplace alone. The recalibration pulls raw coverage back toward the
0.90 target, and the portfolio collapses the loss rate against Laplace.
| stratum | raw cov | @lap cov | raw loss | &lap loss |
|---|---|---|---|---|
| economic change-series, business-daily | 0.84 | 0.92 | 59% | 32% |
| economic change-series, weekly | 0.82 | 0.90 | 51% | 15% |
| economic change-series, monthly (annual cycle) | 0.80 | 0.90 | 38% | 7% |
| M4 hourly, strongly seasonal | 0.76 | 0.89 | 46% | 1% |
| asset prices and returns, daily | 0.82 | 0.92 | 33% | 5% |
Central-90% coverage (0.90 target) and the fraction of series where the arm loses to Laplace by a Diebold–Mariano test.
Protocol
Fixed 128-length context, rolling one-step test window, no fitting, each model in its own environment. Strata split the cached FRED universe and the M4-hourly set by frequency and regime. Full method on the sidecar pattern page and in the methodology.
Existing benchmarks
TiRex reports strongly on public forecasting leaderboards, which measure a different task than this study. Those rank multi-horizon accuracy on curated dataset collections; this study scores one-step-ahead density forecasts on economic change-series against Laplace. A model can lead one and trail the other, so the results here sit alongside, not against, the leaderboards below.
- GIFT-Eval — Salesforce's general forecasting benchmark: 7 domains, about 98 dataset configs, multi-horizon point and quantile accuracy on the series levels. TiRex reports at the top of it, a 35M model ahead of far larger ones.
- Chronos-ZS / fev-leaderboard — AutoGluon's zero-shot leaderboard over the Chronos evaluation datasets, where TiRex also reports strongly.
- Paper benchmarks (NeurIPS 2025) — The authors' own long- and short-horizon evaluation against TabPFN-TS, Chronos-Bolt, TimesFM, and Moirai.
- Third-party analysis — An independent write-up of TiRex's leaderboard results.
Architecture and methodology
TiRex is built on the xLSTM recurrent architecture rather than attention, at 35M parameters. It ingests the context and emits nine quantiles directly in one pass, and is trained for in-context zero-shot forecasting across both short and long horizons. Its small size is the notable part: it leads public leaderboards while being an order of magnitude smaller than the transformer foundation models.