Aloha! 🌺Introducing Ornith-1.5, a family of open-source LLMs spanning 9B Dense, 35B MoE, and 397B MoE, trained with self-improving strategies.
It achieves state-of-the-art performance among open-source models of comparable size and delivers performance comparable to Claude Opus 4.8 across reasoning, agentic, and coding tasks:
✅Terminal-Bench 2.1 (86.1)
✅SWE-Bench (86 on verified, 65.1 on pro, 79.6 on Multilingual)
✅DeepSWE (56)
✅HLE (44.6)
✅ClawEval (81.4)
✅Tool Decathlon (71.2)
Ornith-1.5 takes a major step toward training foundation models through end-to-end self-improvement, extending the self-scaffolding strategies introduced in Ornith-1.0 into a more complete self-improvement loop: the model proposes new tasks, generates task-specific scaffolds, and produces solution rollouts for reinforcement learning, continuously creating new learning experiences from which it can improve.
All models, along with their quantized versions (FP8, GGUF, MLX, and NVFP4), have been released under the MIT License, enabling unrestricted commercial and research use.
📘Tech Blog: https://t.co/OZ63scRWLB
🤗Huggingface: https://t.co/mGJLwhrQOM
@PrimeIntellect curl: (35) LibreSSL/3.3.6: error:1404B42E:SSL routines:ST_CONNECT:tlsv1 alert protocol version
error: could not resolve latest Prime Agent version from https://t.co/knljE7fDdM
The new landing page of @stripe shows the global GDP running on Stripe with a simple algorithm.
Based on this algorithm, Stripe will acquire 100% GDP in the year 2299.
Only 273 more years to go
🗞️Duy Tran has improved the instant switching between iPadOS and iOS on iPhones. This enhancement will soon be integrated into misaka26🔥
https://t.co/ZgRTP5oEPV