Cascade MoE on Bittensor beats Salesforce's Moirai2 on GIFT-Eval 19 days after launch
const_reborn · x · 2026-11-19
Just 19 days after launching, Bittensor's Cascade MoE scored 0.511 on the GIFT-Eval CRPS benchmark, beating Salesforce's leading forecasting model Moirai2 by 0.005, and reached 86.2% parity with Mistral's frontier model on MASE point-forecast accuracy.
The poster frames it as Proof of Useful Work: state-of-the-art forecasters built from latent GPU and talent networks, accessible to all on Bittensor. A public scoreboard is available.
More from Infra
- DNeo: Better Target Feature Encoding Speeds Up Speculative-Diffusion LLM Inference — cerebras · 2026-11-19
- vLLM v0.34.0 Lands: 1,061 Commits, Up to 1.95x Faster Decode on GB200 — vllm_project · 2026-11-19
- Sciforium hits 1,129 output tokens/sec P90 on DeepSeek-V4.1-Flash over 4 AMD MI355X GPUs — rohanpaul_ai · 2026-11-19
- Running untrusted agents on GKE: sandboxing, cold starts, and state — rseroter · 2026-11-19
- OpenAI models find up to 14% PPA gains on AMD GPU IP, improve custom Jalapeño chip — OpenAI · 2026-11-19
- A Local Model for Every Device: 6 Free Offline Models from Phones to Servers — alex_verem · 2026-11-19