GPT-5.6 Luna vs GPT-5.6 Terra
Head-to-head technical comparison of intelligence, capabilities, and API pricing.
Which should you use?
GPT-5.6 Terra leads on the composite index by 1.9 points (92 vs 93.9).
Cost is the sharper difference: GPT-5.6 Terra is 10x the input price of GPT-5.6 Luna ($2 against $0.2 per 1M), so at volume the choice is usually decided by budget rather than benchmarks.
Pick GPT-5.6 Luna when
- Cheaper input tokens — $0.2 against $2 per 1M, so GPT-5.6 Terra costs 10x as much to feed.
- Better value per point of measured capability: $0.002 per index point against $0.021.
Pick GPT-5.6 Terra when
- Higher composite index — 93.9 against 92, a gap of 1.9 points.
- Ahead on Arena Elo by 15 points (1470 vs 1455), which is outside the board's published confidence intervals.
- Stronger on MMLU-Pro: 93.5% against 92%.
Value per point of measured capability, at list input pricing: GPT-5.6 Luna $0.002 · GPT-5.6 Terra $0.021 per index point. Run your own token mix through the token cost calculator — a comparison at list price ignores caching and batch discounts, which move real bills more than this gap does.
Where these numbers come from
Figures as of 2026-09-14. Arena Elo and pricing are read from the public board and each vendor's own pricing page; see the full leaderboard for all 34 models and which columns are measured rather than estimated, or the benchmark matrix for scores benchmark by benchmark.
Our reporting on OpenAI
OpenAI EU Text Watermark: 25% Word Swaps Drop Detection to 17%
OpenAI is rolling out invisible textGrain watermarks to EU ChatGPT and Codex output, but its own tests show replacing 25% of words drops detection from 92% to 17%.
12 Lines of Code Could Hijack ChatGPT’s Mac App
A patched ChatGPT macOS flaw let local malicious code reach chat logs and issue trusted commands through the app, WIRED reports.
Generate and Run a Python Expression with Outlines
Use Outlines and GPT-4o mini to turn a word problem into a Python expression, execute it, and understand the risks of eval.