GPT-5.6 Luna Benchmarks, Pricing & Rankings
OpenAI · 2026-06-05 · Closed · Current
Snapshot 2026-10-14 · updated weekly
GPT-5.6 Luna ranks #31 of 42 on the AMR leaderboard.
GPT-5.6 Luna benchmark scores
| GPQA Diamond | 74.2% | |
| MMLU-Pro | 72.8% | |
| SWE-Bench Verified | 48.9% | |
| AIME 2025 | 71.4% | |
| LiveCodeBench v6 | 62.8% | |
| Arena Elo | 1341 |
GPT-5.6 Luna price, speed & context
Input price
$1.20
per 1M tokens
Output price
$5.50
per 1M tokens
Speed
286
tok/s
Context
512K
tokens
About GPT-5.6 Luna
GPT-5.6 Luna is OpenAI’s speed-first model at 286 tok/s median output — the latency pick for voice and real-time assistants.
Models around GPT-5.6 Luna in the rankings
More OpenAI models
GPT-5.6 Luna FAQ
Where does GPT-5.6 Luna rank?
GPT-5.6 Luna ranks #31 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 78.4. Its strongest dimension is GPQA Diamond at 74.2%.
How much does GPT-5.6 Luna cost?
GPT-5.6 Luna costs $1.20 per million input tokens and $5.50 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $4.42 per million tokens.
What is the GPT-5.6 Luna context window?
GPT-5.6 Luna supports a 512K token context window and generates at a median 286 output tokens per second. That context fits roughly 341 standard documents in a single prompt.
Is GPT-5.6 Luna open source?
No — GPT-5.6 Luna is a closed model available only through OpenAI’s official API and authorized cloud partners.
What is better than GPT-5.6 Luna?
MiniMax H3 Flash ranks one place higher at #30 with an AMR score of 78.8. GPT-5.6 Luna still wins 6 of the tracked dimensions head-to-head — check the comparison table to see exactly which.