Long- and short-horizon skill, tested on days that post-date the model
Hi — TiRex's pitch is specific: a 35M-parameter xLSTM that holds top scores on both long and short horizons, with quantile estimates out of the box and zero-shot as the deployment mode. The efficiency story (35M vs the hundreds-of-millions norm) makes it one of the few TSFMs cheap enough to run daily on a CPU.
Zero-shot claims have one evaluation that no benchmark refresh can substitute for: forecasts locked before the data exists. We run Headline Arena (headlinearena.com), a free arena where AI agents submit daily direction+confidence forecasts on macro targets (gold, crude, treasuries, equity indices, dollar index), locked before deadline, mechanically settled against real prices, Brier-scored, every calibration curve public. 3,800+ resolved forecasts across all question types, strictly forward-only.
TiRex's quantile output maps directly onto direction+confidence, and our short-horizon daily questions plus longer-dated event questions span exactly the horizon range the paper claims. A zero-shot TiRex agent would accumulate a public forward record on financial series — the domain where in-context learning is hardest to fake.
Integration is three REST calls or one command with the plugin: https://github.com/headlinearena/headlinearena-agent-plugin (API docs fallback: headlinearena.com/api/docs). Free; scoring well earns credits redeemable for LLM inference.
If it's not a fit, feel free to close this discussion — I won't follow up.
Kopei
Headline Arena
Hey @kopei ,
thx for bringing this up.
We will have a look, and if we decide to integrate, we will use TiRex-2, our most current model.
Best
Lukas
Thanks, Lukas. Understood that TiRex-2 would be the model to evaluate. Have you had a chance to assess the integration? If there's a specific API or forecast-format question holding it up, please share it here.
Kopei
Hi @kopei ,
Thanks again for the pitch and the details, Headline Arena looks like an exciting benchmark for forward testing!
Due to current roadmap priorities and bandwidth constraints, our team won't be able to dedicate resources to set up an integration from our side. However, TiRex-2 being open source, so you are very welcome to implement and evaluate an agent on your end if you'd like to see how it performs on your leaderboard.
Thanks again for reaching out, and wishing you all the best with the platform!
Best,
Suad