Model comparison
GPT-5.4 Pro vs GPT-5.5 Pro
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 58.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
Summary
- They share 11 benchmarks with published results for both. GPT-5.4 Pro scores higher in 1 category and GPT-5.5 Pro in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.5 Pro leads 84.0 to 72.4.
- The biggest single-benchmark swing is FrontierMath Tier 4: 58.5% for GPT-5.4 Pro and 78% for GPT-5.5 Pro.
- Both cost about the same: $30 input and $180 output per million tokens.
Side by side
| GPT-5.4 Pro | GPT-5.5 Pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 58.9 | 64.3 |
| Released | 2026-03-05 | 2026-04-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $30 | $30 |
| Output $ / M tokens | $180 | $180 |
| Results tracked | 16 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.4 Pro: 43.2 (#90), GPT-5.5 Pro: —
| Benchmark | GPT-5.4 Pro | GPT-5.5 Pro |
|---|---|---|
| WeirdML | 57.4% | — |
Reasoning GPT-5.5 Pro leads
GPT-5.4 Pro: 70.7 (#13), GPT-5.5 Pro: 73.3 (#10)
| Benchmark | GPT-5.4 Pro | GPT-5.5 Pro |
|---|---|---|
| ARC-AGI-2 | 83.3% | 84.6% |
| SimpleBench | 74.1% | 76.9% |
| ARC-AGI-1 | 94.5% | 96.5% |
| CritPt | 30% | 30.6% |
| Chess Puzzles | 58.6% | 64% |
| Epoch Capabilities Index | 158.93 | 162.07 |
| EnigmaEval | 23.8% | — |
| DTBench | — | 96% |
| LMCA | — | 53.9% |
Math GPT-5.5 Pro leads
GPT-5.4 Pro: 72.4 (#22), GPT-5.5 Pro: 84.0 (#10)
| Benchmark | GPT-5.4 Pro | GPT-5.5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | 87.7% |
| FrontierMath Tier 4 | 58.5% | 78% |
| FrontierMath (Feb 2025 set) | 50% | 52.4% |
| FrontierMath Tier 4 (v1) | 37.5% | 39.6% |
| OTIS Mock AIME 2024-2025 | — | 100% |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), GPT-5.5 Pro: 64.1 (#19)
| Benchmark | GPT-5.4 Pro | GPT-5.5 Pro |
|---|---|---|
| GPQA Diamond | 94.6% | 93.9% |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
Frequently asked questions
Is GPT-5.4 Pro better than GPT-5.5 Pro?
GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 58.9 on the Noometry Index.
Which is cheaper, GPT-5.4 Pro or GPT-5.5 Pro?
GPT-5.5 Pro is cheaper. It lists at $30 per million input tokens and $180 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Which has the bigger context window?
Both accept 1.05M tokens.
How many benchmarks do GPT-5.4 Pro and GPT-5.5 Pro share?
11 benchmarks have published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and GPT-5.5 Pro has 14.