Model comparison
o3-mini vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 36.7 on the Noometry Index.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. o3-mini scores higher in 1 category and Step 3.5 Flash in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 42.6 to 28.1.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- 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-mini | Step 3.5 Flash | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 36.7 | 42.3 |
| Released | 2024-12-20 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | 200K | 256K |
| Max output | 100K | 256K |
| Input $ / M tokens | $1.10 | $0.10 |
| Output $ / M tokens | $4.40 | $0.30 |
| Results tracked | 51 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
o3-mini: 40.8 (#132), Step 3.5 Flash: 42.4 (#105)
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1378 | 1436 |
| Aider Polyglot | 60.4% | — |
| SciCode | 39.8% | — |
| GSO | 1.3% | — |
| WeirdML | 43.7% | — |
| LiveBench Coding | 82.7% | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
o3-mini: 29.6 (#84), Step 3.5 Flash: —
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| Cybench | 22.5% | — |
Reasoning Step 3.5 Flash leads
o3-mini: 16.3 (#305), Step 3.5 Flash: 22.2 (#202)
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1366 | 1411 |
| ARC-AGI-2 | 3% | — |
| SimpleBench | 22.8% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 34.5% | — |
| CritPt | 0.3% | — |
| Chess Puzzles | 17% | — |
| LiveBench Reasoning | 89.6% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LiveBench Data Analysis | 70.6% | — |
| LMCA | 19% | — |
| Epoch Capabilities Index | 140.34 | — |
| ForecastBench | 59.6 | — |
| LiveBench | 75.9% | — |
Math Step 3.5 Flash leads
o3-mini: 28.1 (#244), Step 3.5 Flash: 42.6 (#84)
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1396 | 1408 |
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 76.9% | — |
| LiveBench Math | 77.3% | — |
| MATH Level 5 | 96.5% | — |
| FrontierMath (Feb 2025 set) | 12.4% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Step 3.5 Flash leads
o3-mini: 38.3 (#146), Step 3.5 Flash: 39.6 (#132)
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1364 | 1421 |
| GPQA Diamond | 77% | — |
| SimpleQA Verified | 15.3% | — |
| Confabulations | 17.9% | — |
Multilingual Step 3.5 Flash leads
o3-mini: 45.7 (#164), Step 3.5 Flash: 50.5 (#119)
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1319 | 1385 |
| LMArena Chinese | 1379 | 1447 |
| LMArena French | 1334 | 1421 |
| LMArena German | 1303 | 1405 |
| LMArena Japanese | 1286 | 1354 |
| LMArena Korean | 1314 | 1352 |
| LMArena Russian | 1304 | 1385 |
| LMArena Spanish | 1321 | 1419 |
Instruction Following o3-mini leads
o3-mini: 75.1 (#72), Step 3.5 Flash: 73.1 (#124)
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1337 | 1385 |
| LiveBench Instruction Following | 84.4% | — |
Long Context Step 3.5 Flash leads
o3-mini: 33.8 (#256), Step 3.5 Flash: 42.8 (#117)
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1343 | 1402 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Step 3.5 Flash leads
o3-mini: 50.3 (#182), Step 3.5 Flash: 58.8 (#113)
| Benchmark | o3-mini | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1337 | 1403 |
| LMArena Creative Writing | 1286 | 1357 |
| LMArena Multi-Turn | 1320 | 1405 |
| Short-Story Creative Writing | 61.7% | — |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 36.7 on the Noometry Index.
Which is cheaper, o3-mini 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-mini lists at $1.10 and $4.40.
Is o3-mini or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 40.8 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-mini and Step 3.5 Flash share?
17 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Step 3.5 Flash has 19.