Model comparison
GPT-5.4 Pro vs Step 5 Preview
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 47.9 on the Noometry Index. Step 5 Preview costs 47× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
StepFunSummary
- They share 1 benchmark with published results for both. GPT-5.4 Pro scores higher in 3 categories and Step 5 Preview in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 40.0.
- The biggest single-benchmark swing is CritPt: 30% for GPT-5.4 Pro and 20.9% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 1.02M.
Side by side
| GPT-5.4 Pro | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 58.9 | 47.9 |
| Released | 2026-03-05 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.02M |
| Max output | 128K | 66K |
| Input $ / M tokens | $30 | $1 |
| Output $ / M tokens | $180 | $2.70 |
| Results tracked | 16 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
GPT-5.4 Pro: 43.2 (#90), Step 5 Preview: 51.8 (#36)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 57.4% | — |
| LMArena Coding | — | 1480 |
Reasoning GPT-5.4 Pro leads
GPT-5.4 Pro: 70.7 (#13), Step 5 Preview: 40.0 (#57)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| CritPt | 30% | 20.9% |
| ARC-AGI-2 | 83.3% | — |
| SimpleBench | 74.1% | — |
| ARC-AGI-1 | 94.5% | — |
| Chess Puzzles | 58.6% | — |
| EnigmaEval | 23.8% | — |
| LMArena Hard Prompts | — | 1465 |
| Epoch Capabilities Index | 158.93 | — |
Math GPT-5.4 Pro leads
GPT-5.4 Pro: 72.4 (#22), Step 5 Preview: 46.1 (#72)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| FrontierMath (Tiers 1-3) | 82.5% | — |
| FrontierMath Tier 4 | 58.5% | — |
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
| FrontierMath (Feb 2025 set) | 50% | — |
| FrontierMath Tier 4 (v1) | 37.5% | — |
Knowledge GPT-5.4 Pro leads
GPT-5.4 Pro: 68.3 (#7), Step 5 Preview: 41.2 (#112)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| GPQA Diamond | 94.6% | — |
| Humanity's Last Exam | 44.3% | — |
| SimpleQA Verified | 46.3% | — |
| Vectara Hallucination Rate | 8.3% | — |
| LMArena Expert | — | 1470 |
Multimodal Not comparable
GPT-5.4 Pro: —, Step 5 Preview: 41.0 (#41)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
GPT-5.4 Pro: —, Step 5 Preview: 53.8 (#54)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
GPT-5.4 Pro: —, Step 5 Preview: 76.0 (#50)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
GPT-5.4 Pro: —, Step 5 Preview: 44.5 (#64)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
GPT-5.4 Pro: —, Step 5 Preview: 62.8 (#71)
| Benchmark | GPT-5.4 Pro | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is GPT-5.4 Pro better than Step 5 Preview?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 47.9 on the Noometry Index. Step 5 Preview costs 47× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.4 Pro or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GPT-5.4 Pro or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 43.2 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 1.02M.
How many benchmarks do GPT-5.4 Pro and Step 5 Preview share?
1 benchmark has published results for both models. GPT-5.4 Pro has 16 scored results on Noometry and Step 5 Preview has 18.