Model comparison
o3-pro vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 42.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in long context, where o3-pro leads 72.2 to 44.5.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $20 / $80 for o3-pro.
- Step 5 Preview accepts more context: 1.02M tokens versus 200K.
Side by side
| o3-pro | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 42.9 | 47.9 |
| Released | 2025-06-10 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.02M |
| Max output | 100K | 66K |
| Input $ / M tokens | $20 | $1 |
| Output $ / M tokens | $80 | $2.70 |
| Results tracked | 12 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-pro: 55.5 (#24), Step 5 Preview: 51.8 (#36)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| Aider Polyglot | 84.9% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 58.2% | — |
| LMArena Coding | — | 1480 |
Reasoning Step 5 Preview leads
o3-pro: 23.8 (#171), Step 5 Preview: 40.0 (#57)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 72.1% | — |
| ARC-AGI-1 | 59.3% | — |
| CritPt | — | 20.9% |
| LMArena Hard Prompts | — | 1465 |
| DTBench | 86.9% | — |
| LMCA | 38.5% | — |
| Epoch Capabilities Index | 147.42 | — |
Math Not comparable
o3-pro: —, Step 5 Preview: 46.1 (#72)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
Knowledge Step 5 Preview leads
o3-pro: 29.5 (#238), Step 5 Preview: 41.2 (#112)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 23.3% | — |
| LMArena Expert | — | 1470 |
Multimodal Not comparable
o3-pro: —, Step 5 Preview: 41.0 (#41)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
o3-pro: —, Step 5 Preview: 53.8 (#54)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
o3-pro: —, Step 5 Preview: 76.0 (#50)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), Step 5 Preview: 44.5 (#64)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | — | 1455 |
Writing & Preference Step 5 Preview leads
o3-pro: 57.1 (#133), Step 5 Preview: 62.8 (#71)
| Benchmark | o3-pro | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| Short-Story Creative Writing | 84.4% | — |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is o3-pro better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 42.9 on the Noometry Index.
Which is cheaper, o3-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; o3-pro lists at $20 and $80.
Is o3-pro or Step 5 Preview better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 51.8 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 200K.
How many benchmarks do o3-pro and Step 5 Preview share?
0 benchmarks have published results for both models. o3-pro has 12 scored results on Noometry and Step 5 Preview has 18.