GPT-5.4 Pro vs GPT-5.5 Pro
GPT-5.4 Pro Verdict
- GPT-5.5 Pro (xhigh) leads on quality: 67.1 vs 64.3.
- GPT-5.4 Pro is stronger in instruction following, knowledge, multimodal.
- GPT-5.5 Pro (xhigh) is stronger in reasoning, maths.
- They cost about the same ($67.50 per 1M blended).
- GPT-5.5 Pro (xhigh) streams 4.0× faster (4 vs 1 tokens per second).
| Metric | GPT-5.4 Pro | GPT-5.5 Pro (xhigh) |
|---|---|---|
| BenchLeader Index | 64.3 | 67.1 |
| Instruction following score | 67.3 | – |
| Knowledge score | 73.6 | – |
| Multimodal score | 69.8 | – |
| Reasoning score | 75.3 | 80.1 |
| Maths score | – | 74.5 |
| Blended price $/M | $67.50 | $67.50 |
| Output speed | 1 tok/s | 4 tok/s |
| Time to first answer | 5.8 s | 3.5 s |
| Context window | 1.1M | 1.1M |
| FrontierMath Tiers 1–3 | – | 87.7% |
| FrontierMath Tier 4 | – | 78.0% |
| Humanity's Last Exam | 44.3% | – |
| SimpleBench | 74.1% | – |
| Epoch Capabilities Index | 158.9 | – |
| MultiChallenge | 69.2% | – |
| VISTA | 53.9% | – |
| MultiNRC | 62.3% | – |
| TutorBench | 56.6% | – |
| ARC-AGI-1 | – | 95.0% |
| ARC-AGI-2 | – | 84.2% |
| CritPt | – | 30.6% |
| FORTRESS | 14.8% | – |
| MASK | 91.7% | – |
| LMCA | – | 53.9% |
| DTBench | – | 96.0% |
Data as of 2026-09-19. Best configuration of each model; every score links to its source on the model pages.
GPT-5.4 Pro vs GPT-5.5 Pro: questions
- Is GPT-5.4 Pro better than GPT-5.5 Pro?
- GPT-5.5 Pro (xhigh) leads on quality: 67.1 vs 64.3. The BenchLeader Index combines every independent quality benchmark; GPT-5.5 Pro (xhigh) is ahead overall as of 2026-09-19, but check the category scores for your use.
- Which is cheaper, GPT-5.4 Pro or GPT-5.5 Pro?
- GPT-5.4 Pro is cheaper: $67.50 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 Pro?
- GPT-5.5 Pro streams faster: 4 against 1 output tokens per second.
- Which has the larger context window?
- Both accept 1.1M tokens of context.