France's t0-beta, a 256M-parameter open time-series foundation model, hits top-3 on GIFT-Eval and fev-bench
AxSaucedo · x · 2026-09-23
The Forecasting Company (France) released t0-beta, an open 256M-parameter time-series forecasting foundation model that ranks third among zero-shot checkpoints on both major public benchmarks:
- GIFT-Eval: CRPS 0.4738 / MASE 0.6865, behind only Google TimesFM-3.0 (331M) and IBM Granite-PatchTST-FM; a 4.1% CRPS and 5.2% MASE improvement over its t0-alpha.
- fev-bench: 46.7% skill score, +4.5 points over t0-alpha, trailing Google and Amazon Chronos-2; also third on the 42 covariate tasks.
A single checkpoint, no task-specific retraining. Notably, 256M parameters beat Datadog's 2.45B Toto-2.0-2.5B. Weights are on Hugging Face with a tech report.
More from Models
- GPT-6 Sol accused of ignoring configured skills that work fine on GPT-5.6 — Aber-so-richtig · 2026-09-23
- Opus 5.5 ultra wows with 4-agent, 90-minute fully-from-scratch build — repligate · 2026-09-23
- No Kimi release this week, says leaker: Moonshot staff go on holiday Friday — ChrisGPT · 2026-09-23
- Screenshot suggests GPT-5.6 Sol is free for ChatGPT Go subscribers on Windows — sam619007 · 2026-09-23
- Opus 5.5 wins the day as GPT-6 Sol skips ChatGPT, sparking model debate — koltregaskes · 2026-09-23
- Opus 5.5 becomes a daily driver: faster, cheaper than Opus 5, plus reset credits — addyosmani · 2026-09-23