BenchLeader

GPT-5.4 Pro vs GPT-5.6 Luna

Verdict
  • GPT-5.4 Pro leads on quality: 64.3 vs 57.9.
  • GPT-5.4 Pro is stronger in instruction following, knowledge, multimodal, reasoning.
  • GPT-5.6 Luna (xhigh) is stronger in agents & tools, coding, composite, human preference, long context.
  • GPT-5.6 Luna (xhigh) is 150× cheaper ($0.450 vs $67.50 per 1M blended).
  • GPT-5.6 Luna (xhigh) streams 117.6× faster (118 vs 1 tokens per second).
MetricGPT-5.4 ProGPT-5.6 Luna (xhigh)
BenchLeader Index64.357.9
Instruction following score67.3
Knowledge score73.655.5
Multimodal score69.860.9
Reasoning score75.353.9
Agents & tools score48.7
Coding score59.8
Composite score66.6
Human preference score65.0
Long context score65.1
Blended price $/M$67.50$0.450
Output speed1 tok/s118 tok/s
Time to first answer6.3 s46.5 s
Context window1.1M1.1M
Humanity's Last Exam44.3%
SimpleBench74.1%46.8%
SciCode50.0%
Epoch Capabilities Index158.9
LMArena Text1453
LMArena Hard Prompts1473
LMArena Coding1498
LMArena WebDev1519
LMArena Vision1254
LMArena Agent0.7
AA Intelligence Index34.8
AA-LCR81.7%
MMMU-Pro78.5%
AA-Omniscience-10.8
GPQA Diamond (AA)89.5%
Humanity's Last Exam (AA)37.0%
SciCode (AA)50.5%
MultiChallenge69.2%
VISTA53.9%
MultiNRC62.3%
TutorBench56.6%
ARC-AGI-187.7%
ARC-AGI-247.6%
ARC-AGI-30.0%

Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.

GPT-5.4 Pro vs GPT-5.6 Luna: questions

Is GPT-5.4 Pro better than GPT-5.6 Luna?
GPT-5.4 Pro leads on quality: 64.3 vs 57.9. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 Pro is ahead overall as of 2026-09-13, but check the category scores for your use.
Which is cheaper, GPT-5.4 Pro or GPT-5.6 Luna?
GPT-5.6 Luna is cheaper: $0.450 against $67.50 per million tokens, blended at three input tokens per output token.
Which is faster, GPT-5.4 Pro or GPT-5.6 Luna?
GPT-5.6 Luna streams faster: 118 against 1 output tokens per second.
Which has the larger context window?
Both accept 1.1M tokens of context.