Model comparison
o3-pro vs Step 3.5 Flash
o3-pro is the stronger model overall, scoring 42.7 to 41.7 on the Noometry Index. Step 3.5 Flash costs 233× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in long context, where o3-pro leads 72.1 to 42.8.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $20 / $80 for o3-pro.
- Step 3.5 Flash accepts more context: 256K tokens versus 200K.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| o3-pro | Step 3.5 Flash | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 42.7 | 41.7 |
| Released | 2025-06-10 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | 200K | 256K |
| Max output | 100K | 256K |
| Input $ / M tokens | $20 | $0.10 |
| Output $ / M tokens | $80 | $0.30 |
| Results tracked | 12 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-pro: 55.1 (#22), Step 3.5 Flash: 41.7 (#106)
| Benchmark | o3-pro | Step 3.5 Flash |
|---|---|---|
| Aider Polyglot | 84.9% | — |
| WeirdML | 58.2% | — |
| LMArena Coding | — | 1436 |
Reasoning o3-pro leads
o3-pro: 24.1 (#152), Step 3.5 Flash: 21.2 (#202)
| Benchmark | o3-pro | Step 3.5 Flash |
|---|---|---|
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 72.1% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 59.3% | — |
| LMArena Hard Prompts | — | 1411 |
| DTBench | 86.9% | — |
| LMCA | 38.5% | — |
| Epoch Capabilities Index | 147.43 | — |
Math Not comparable
o3-pro: —, Step 3.5 Flash: 40.6 (#77)
| Benchmark | o3-pro | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 66.8% |
| LMArena Math | — | 1408 |
Knowledge Step 3.5 Flash leads
o3-pro: 29.0 (#234), Step 3.5 Flash: 39.0 (#127)
| Benchmark | o3-pro | Step 3.5 Flash |
|---|---|---|
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 23.3% | — |
| LMArena Expert | — | 1422 |
Multilingual Not comparable
o3-pro: —, Step 3.5 Flash: 50.7 (#115)
| Benchmark | o3-pro | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | — | 1386 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1421 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1419 |
Instruction Following Not comparable
o3-pro: —, Step 3.5 Flash: 73.3 (#119)
| Benchmark | o3-pro | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | — | 1385 |
Long Context o3-pro leads
o3-pro: 72.1 (#1), Step 3.5 Flash: 42.8 (#112)
| Benchmark | o3-pro | Step 3.5 Flash |
|---|---|---|
| Fiction.LiveBench | 97.2% | — |
| LMArena Longer Query | — | 1402 |
Writing & Preference Step 3.5 Flash leads
o3-pro: 57.1 (#128), Step 3.5 Flash: 59.0 (#108)
| Benchmark | o3-pro | Step 3.5 Flash |
|---|---|---|
| LMArena Text | — | 1403 |
| LMArena Creative Writing | — | 1357 |
| Short-Story Creative Writing | 84.4% | — |
| LMArena Multi-Turn | — | 1405 |
Frequently asked questions
Is o3-pro better than Step 3.5 Flash?
o3-pro is the stronger model overall, scoring 42.7 to 41.7 on the Noometry Index. Step 3.5 Flash costs 233× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, o3-pro or Step 3.5 Flash?
Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; o3-pro lists at $20 and $80.
Is o3-pro or Step 3.5 Flash better for coding?
o3-pro scores higher on coding benchmarks: 55.1 versus 41.7 in the Noometry coding category.
Which has the bigger context window?
Step 3.5 Flash does, with 256K tokens against 200K.
How many benchmarks do o3-pro and Step 3.5 Flash share?
0 benchmarks have published results for both models. o3-pro has 12 scored results on Noometry and Step 3.5 Flash has 19.