Model comparison
o3 vs Step 3.5 Flash
o3 is the stronger model overall, scoring 47.5 to 42.3 on the Noometry Index. Step 3.5 Flash costs 23× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. o3 scores higher in 7 categories and Step 3.5 Flash in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 39.6.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $2 / $8 for o3.
- 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 | Step 3.5 Flash | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 47.5 | 42.3 |
| Released | 2025-04-16 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | 200K | 256K |
| Max output | 100K | 256K |
| Input $ / M tokens | $2 | $0.10 |
| Output $ / M tokens | $8 | $0.30 |
| Results tracked | 63 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3 leads
o3: 46.8 (#64), Step 3.5 Flash: 42.4 (#105)
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1408 | 1436 |
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Step 3.5 Flash: —
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
Reasoning o3 leads
o3: 32.0 (#78), Step 3.5 Flash: 22.2 (#202)
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1402 | 1411 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 60.8% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 38% | — |
| EnigmaEval | 13.1% | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 84.8% | — |
| LMCA | 39.7% | — |
| Epoch Capabilities Index | 146.86 | — |
| ForecastBench | 62.5 | — |
Math o3 leads
o3: 50.2 (#58), Step 3.5 Flash: 42.6 (#84)
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1426 | 1408 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| Omni-MATH | 71.4% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 18.7% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge o3 leads
o3: 54.6 (#52), Step 3.5 Flash: 39.6 (#132)
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1402 | 1421 |
| GPQA Diamond | 81.8% | — |
| Humanity's Last Exam | 20.3% | — |
| SimpleQA Verified | 49.4% | — |
| MMLU-Pro | 85.9% | — |
| Confabulations | 14.4% | — |
| GPQA (HELM) | 75.3% | — |
Multimodal Not comparable
o3: 41.4 (#36), Step 3.5 Flash: —
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Vision | 1214 | — |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual o3 leads
o3: 51.7 (#105), Step 3.5 Flash: 50.5 (#119)
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1401 | 1385 |
| LMArena Chinese | 1437 | 1447 |
| LMArena French | 1430 | 1421 |
| LMArena German | 1420 | 1405 |
| LMArena Japanese | 1403 | 1354 |
| LMArena Korean | 1370 | 1352 |
| LMArena Russian | 1406 | 1385 |
| LMArena Spanish | 1395 | 1419 |
Instruction Following Too close to call
o3: 72.8 (#127), Step 3.5 Flash: 73.1 (#124)
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1368 | 1385 |
| IFEval | 86.9% | — |
Long Context o3 leads
o3: 53.3 (#6), Step 3.5 Flash: 42.8 (#117)
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1372 | 1402 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference o3 leads
o3: 63.5 (#64), Step 3.5 Flash: 58.8 (#113)
| Benchmark | o3 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1410 | 1403 |
| LMArena Creative Writing | 1359 | 1357 |
| LMArena Multi-Turn | 1405 | 1405 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
Frequently asked questions
Is o3 better than Step 3.5 Flash?
o3 is the stronger model overall, scoring 47.5 to 42.3 on the Noometry Index. Step 3.5 Flash costs 23× less per token, which makes it the better buy when o3's lead doesn't matter for your workload.
Which is cheaper, o3 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 lists at $2 and $8.
Is o3 or Step 3.5 Flash better for coding?
o3 scores higher on coding benchmarks: 46.8 versus 42.4 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 and Step 3.5 Flash share?
17 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Step 3.5 Flash has 19.