GPT-5.6 Terra
A mid-tier model in the GPT-5.6 series designed for high-frequency everyday workloads. Its performance matches GPT-5.5 at a lower price point, and its Coding Agent Index score is slightly higher than that of Fable 5.
Timeline (last 90 days)
According to data published by OpenAI, on the Agents Last Exam benchmark, at medium reasoning effort, GPT-6.1 Terra scored 57.6% and GPT-5.6 Terra scored 42.6%, an improvement of 15 percentage points.
Starting November 16, 2026, three models—Claude Opus 4.8, Claude Opus 5, and GPT-5.6 Terra—will be removed from GitHub Copilot's Chat, inline editing, ask and agent modes, and code completion.
Swapping Terra for Luna is a complete change of magnitude: GitHub's model and pricing table classifies Sol in the top category, Terra in Versatile, and Luna in Lightweight, and Luna's output price is only one twenty-fourth of Terra's ($0.50 vs $12).
GLM-5.3-Flash scores 48.8 on AutomationBench, ahead of Claude Opus 4.8's 41.0 and GPT-5.6 Terra's 37.2, at a per-task cost of about $0.045.
GLM-5.3-Flash scores 84.3 on Terminal-Bench 2.1, slightly below Claude Opus 4.8's 85.0 and GPT-5.6 Terra's 87.4.
Of the 46 models, 41 completed all 28 questions, 3 did not finish due to service errors, GPT-5.6 Terra stopped at 24/28 due to quota limits, and GPT-6 Astra only ran 1 question.
Luna's output price dropped from $6 per million tokens to $0.50 within two months, a reduction of more than 90%.
In terms of input token counts, both Astra and Luna used 16 tokens, while Sol and Terra used 26 tokens.
Qwen 3.8 27B surpasses GPT-5.6 Terra, DeepSeek v4 Pro, GPT-5.6 Luna, and Gemini 3.7 Flash on the Agentic index.
According to Artificial Analysis data, Qwen 3.8's 27 billion parameter model scored 51 on the Agentic Index, surpassing GPT-5.6 Terra, DeepSeek v4 Pro, GPT-5.6 Luna, and Gemini 3.7 Flash.
All Facts (5)
According to data published by OpenAI, on the Agents Last Exam benchmark, at medium reasoning effort, GPT-6.1 Terra scored 57.6% and GPT-5.6 Terra scored 42.6%, an improvement of 15 percentage points.
50%UnverifiedSwapping Terra for Luna is a complete change of magnitude: GitHub's model and pricing table classifies Sol in the top category, Terra in Versatile, and Luna in Lightweight, and Luna's output price is only one twenty-fourth of Terra's ($0.50 vs $12).
50%UnverifiedIn terms of input token counts, both Astra and Luna used 16 tokens, while Sol and Terra used 26 tokens.
50%UnverifiedQwen 3.8 27B surpasses GPT-5.6 Terra, DeepSeek v4 Pro, GPT-5.6 Luna, and Gemini 3.7 Flash on the Agentic index.
50%UnverifiedStarting November 16, 2026, three models—Claude Opus 4.8, Claude Opus 5, and GPT-5.6 Terra—will be removed from GitHub Copilot's Chat, inline editing, ask and agent modes, and code completion.
50%