ModelsAug 19, 2026 · 23:598 sources

Ornith 397B Open Model Beats Claude Opus 4.8, Matching Top Closed AI in Coding

From huggingnews.com

Image: huggingnews.com
AI;DR

Ornith has released the Ornith-1.5 family of open source large language models, including 9B Dense, 35B Mixture of Experts (MoE), and 397B MoE variants. The 397B model outperformed Claude Opus 4.8 on four reasoning and coding benchmarks, such as Terminal-Bench 2.1 and SWE-bench Verified, using a reinforcement learning loop. All variants are distributed under the MIT License.

Read the sourceSign in to suggest

Sources

+ 3 more
  1. SUPPORT@rohanpaul_ai“Only 397B weights, but 4 wins over Claude Opus 4.8: Terminal-Bench 2.1 (86.1 v 85), SWE-bench Verified (86 v 85.8), WideSearch (80.8 v 72.9), BrowseComp (86.6 v 84.3)”x.com
  2. SUPPORT@testingcatalog“quantized 9B-Mobile build that targets iPhone and Android, putting a coding agent on device”x.com
  3. SUPPORT@vllm_project“MIT-licensed family from 9B to 397B, SOTA among open models on coding and agentic tasks”x.com

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today