GPT-6.1 Terra surfaces in Microsoft's public code as default judge across 18 eval configs
mark_k · x · 2026-10-20
markk spotted "gpt-6.1-terra" set as the default judge across 18 evaluation configs in an EF Core update Microsoft merged on October 16 — seventeen of them previously used GPT-5.6 Terra. The model performing the coding tasks was also moved to GPT-6.1 Sol.
The notable detail: Terra is configured to grade another AI's work. Microsoft appears to be preparing its coding evaluations around a new generation of both models, though the configs reveal no release date and nothing about how much better Terra is.
Related event: Microsoft PR leak reveals unreleased OpenAI model GPT-6.1 Terra(6 posts)→
More from Models
- GPT-6.1 Terra rolls out to all Plus, Pro, Enterprise and Edu users — OpenAI · 2026-10-27
- OpenAI launches GPT-6.1 Terra with 50% lower API prices than GPT-5.6 Terra — OpenAI · 2026-10-27
- GPT-6.1 Terra API pricing revealed: $1 input / $5 output, $0.05 cached — airesearch12 · 2026-10-27
- In cyber, intention matters little: Chintala on model info leaks, and what users should do — brhydon · 2026-10-27
- Why don't more LLMs ship 10M-token context? A researcher asks about attention tradeoffs — agarwl_ · 2026-10-27
- Ortet's first health eval: 34 open-weight models, 50 tasks, generic rankings fall short — thegautamkamath · 2026-10-27