BenchLeader

GPT-5.4 Pro vs GPT-5.5 Instant

Verdict
  • GPT-5.4 Pro leads on quality: 64.3 vs 60.5.
  • GPT-5.4 Pro is stronger in knowledge, multimodal, reasoning.
  • GPT-5.5 Instant is stronger in instruction following, agents & tools, coding, composite, human preference, long context, maths.
  • GPT-5.5 Instant is 6.0× cheaper ($11.25 vs $67.50 per 1M blended).
  • GPT-5.5 Instant streams 128.5× faster (129 vs 1 tokens per second).
MetricGPT-5.4 ProGPT-5.5 Instant
BenchLeader Index64.360.5
Instruction following score67.369.8
Knowledge score73.669.4
Multimodal score69.859.7
Reasoning score75.362.6
Agents & tools score70.7
Coding score61.1
Composite score62.9
Human preference score67.5
Long context score61.4
Maths score42.5
Blended price $/M$67.50$11.25
Output speed1 tok/s129 tok/s
Time to first answer6.5 s16.8 s
Context window1.1M400k
GPQA Diamond82.5%
FrontierMath Tiers 1–326.3%
FrontierMath Tier 42.4%
OTIS Mock AIME68.1%
Humanity's Last Exam44.3%
SimpleBench74.1%
SciCode48.6%
Epoch Capabilities Index158.9142.5
LMArena Text1474
LMArena Hard Prompts1491
LMArena Coding1514
LMArena Vision1251
AA Intelligence Index26.8
IFBench71.5%
AA-LCR70.0%
AA-Omniscience11.2
Terminal-Bench Hard42.4%
GPQA Diamond (AA)84.7%
Humanity's Last Exam (AA)21.6%
SciCode (AA)52.5%
τ²-Bench Telecom (AA)49.4%
MultiChallenge69.2%
VISTA53.9%
MultiNRC62.3%
TutorBench56.6%

Data as of 2026-09-10. Best configuration of each model; every score links to its source on the model pages.

GPT-5.4 Pro vs GPT-5.5 Instant: questions

Is GPT-5.4 Pro better than GPT-5.5 Instant?
GPT-5.4 Pro leads on quality: 64.3 vs 60.5. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 Pro is ahead overall as of 2026-09-10, but check the category scores for your use.
Which is cheaper, GPT-5.4 Pro or GPT-5.5 Instant?
GPT-5.5 Instant is cheaper: $11.25 against $67.50 per million tokens, blended at three input tokens per output token.
Which is faster, GPT-5.4 Pro or GPT-5.5 Instant?
GPT-5.5 Instant streams faster: 129 against 1 output tokens per second.
Which has the larger context window?
GPT-5.4 Pro accepts more context: 1.1M against 400k tokens.