Model comparison
o3-pro vs Step 3
o3-pro is the stronger model overall, scoring 42.9 to 40.5 on the Noometry Index.
Last verified . 1 shared benchmarks.
StepFunSummary
- They share 1 benchmark with published results for both. o3-pro scores higher in 3 categories and Step 3 in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 40.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 72.1% for o3-pro and 62.3% for Step 3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| o3-pro | Step 3 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 42.9 | 40.5 |
| Released | 2025-06-10 | — |
| Weights | Proprietary | Open |
| Context window | 200K | — |
| Max output | 100K | — |
| Input $ / M tokens | $20 | — |
| Output $ / M tokens | $80 | — |
| Results tracked | 12 | 17 |
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 3: 40.1 (#147)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| Aider Polyglot | 84.9% | — |
| WeirdML | 58.2% | — |
| LMArena Coding | — | 1367 |
Reasoning Step 3 leads
o3-pro: 23.8 (#171), Step 3: 28.4 (#105)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 72.1% | 62.3% |
| ARC-AGI-2 | 4.9% | — |
| ARC-AGI-1 | 59.3% | — |
| LMArena Hard Prompts | — | 1355 |
| DTBench | 86.9% | — |
| LMCA | 38.5% | — |
| Epoch Capabilities Index | 147.42 | — |
Math Not comparable
o3-pro: —, Step 3: 37.6 (#148)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |
Knowledge Step 3 leads
o3-pro: 29.5 (#238), Step 3: 36.8 (#164)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 23.3% | — |
| LMArena Expert | — | 1333 |
Multimodal Not comparable
o3-pro: —, Step 3: 35.5 (#86)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Not comparable
o3-pro: —, Step 3: 46.3 (#159)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1397 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1371 |
Instruction Following Not comparable
o3-pro: —, Step 3: 70.4 (#164)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context o3-pro leads
o3-pro: 72.2 (#1), Step 3: 40.3 (#157)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | — | 1326 |
Writing & Preference o3-pro leads
o3-pro: 57.1 (#133), Step 3: 54.3 (#151)
| Benchmark | o3-pro | Step 3 |
|---|---|---|
| LMArena Text | — | 1350 |
| LMArena Creative Writing | — | 1321 |
| Short-Story Creative Writing | 84.4% | — |
| LMArena Multi-Turn | — | 1341 |
Frequently asked questions
Is o3-pro better than Step 3?
o3-pro is the stronger model overall, scoring 42.9 to 40.5 on the Noometry Index.
Is o3-pro or Step 3 better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 40.1 in the Noometry coding category.
How many benchmarks do o3-pro and Step 3 share?
1 benchmark has published results for both models. o3-pro has 12 scored results on Noometry and Step 3 has 17.