BenchLeader

GPT-5.5 Pro vs GPT-6 Luna

Verdict
  • GPT-5.5 Pro (xhigh) leads on quality: 67.0 vs 61.2.
  • GPT-5.5 Pro (xhigh) is stronger in maths, reasoning.
  • GPT-6 Luna (max) is stronger in composite, knowledge, long context, multimodal.
  • GPT-6 Luna (max) is 338× cheaper ($0.200 vs $67.50 per 1M blended).
  • GPT-6 Luna (max) streams 39.3× faster (157 vs 4 tokens per second).
MetricGPT-5.5 Pro (xhigh)GPT-6 Luna (max)
BenchLeader Index67.061.2
Maths score74.3
Reasoning score80.176.1
Composite score73.9
Knowledge score63.2
Long context score67.5
Multimodal score59.2
Blended price $/M$67.50$0.200
Output speed4 tok/s157 tok/s
Time to first answer3.4 s142.6 s
Context window1.1M1.1M
FrontierMath Tiers 1–387.7%
FrontierMath Tier 478.0%
AA Intelligence Index37.3
AA-LCR83.3%
MMMU-Pro75.5%
AA-Omniscience0.7
Humanity's Last Exam (AA)38.5%
SciCode (AA)54.6%
ARC-AGI-195.0%
ARC-AGI-284.2%
CritPt30.6%19.4%
GDPval (AA)43.4%
LMCA53.9%
DTBench96.0%
Terminal-Bench 4.0 (AA)12.6%
AutomationBench53.2%
GDP.pdf20.4%
MLCR16.1%
AA-Omniscience: accuracy43.8%
AA-Omniscience: non-hallucination23.3%
AA-Briefcase1299

Data as of 2026-09-23. Best configuration of each model; every score links to its source on the model pages.

GPT-5.5 Pro vs GPT-6 Luna: questions

Is GPT-5.5 Pro better than GPT-6 Luna?
GPT-5.5 Pro (xhigh) leads on quality: 67.0 vs 61.2. The BenchLeader Index combines every independent quality benchmark; GPT-5.5 Pro (xhigh) is ahead overall as of 2026-09-23, but check the category scores for your use.
Which is cheaper, GPT-5.5 Pro or GPT-6 Luna?
GPT-6 Luna is cheaper: $0.200 against $67.50 per million tokens, blended at three input tokens per output token.
Which is faster, GPT-5.5 Pro or GPT-6 Luna?
GPT-6 Luna streams faster: 157 against 4 output tokens per second.
Which has the larger context window?
Both accept 1.1M tokens of context.