Model comparison
o3 vs Step 5 Preview
o3 and Step 5 Preview score almost the same on the Noometry Index (47.5 vs 47.9), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. o3 scores higher in 5 categories and Step 5 Preview in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o3 leads 54.6 to 41.2.
- The biggest single-benchmark swing is CritPt: 1.4% for o3 and 20.9% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2 / $8 for o3.
- Step 5 Preview accepts more context: 1.02M tokens versus 200K.
Side by side
| o3 | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 47.5 | 47.9 |
| Released | 2025-04-16 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.02M |
| Max output | 100K | 66K |
| Input $ / M tokens | $2 | $1 |
| Output $ / M tokens | $8 | $2.70 |
| Results tracked | 63 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
o3: 46.8 (#64), Step 5 Preview: 51.8 (#36)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1408 | 1480 |
| SWE-bench Verified | 62.3% | — |
| SWE-bench Verified (bash only) | 58.4% | — |
| Aider Polyglot | 81.3% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| GSO | 8.8% | — |
| WeirdML | 52.4% | — |
| CadEval | 74% | — |
| ALE-Bench | 933.55 | — |
Agentic & Tool Use Not comparable
o3: 34.5 (#44), Step 5 Preview: —
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 63% | — |
| GDPval | 30.8% | — |
| DeepResearch Bench | 45.2% | — |
| OSWorld | 23% | — |
| LMArena Search | 1144 | — |
| METR Time Horizons | 65.4% | — |
Reasoning Step 5 Preview leads
o3: 32.0 (#78), Step 5 Preview: 40.0 (#57)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| CritPt | 1.4% | 20.9% |
| LMArena Hard Prompts | 1402 | 1465 |
| ARC-AGI-2 | 6.5% | — |
| SimpleBench | 53.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 60.8% | — |
| 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 5 Preview: 46.1 (#72)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1426 | 1470 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| OTIS Mock AIME 2024-2025 | 84.4% | — |
| ProofBench | — | 42% |
| 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 5 Preview: 41.2 (#112)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1402 | 1470 |
| 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 Too close to call
o3: 41.4 (#36), Step 5 Preview: 41.0 (#41)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1214 | 1267 |
| GeoBench | 74% | — |
| VPCT | 52% | — |
Multilingual Step 5 Preview leads
o3: 51.7 (#105), Step 5 Preview: 53.8 (#54)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1401 | 1432 |
| LMArena Chinese | 1437 | 1519 |
| LMArena Russian | 1406 | 1436 |
| LMArena Spanish | 1395 | 1439 |
| LMArena French | 1430 | — |
| LMArena German | 1420 | — |
| LMArena Japanese | 1403 | — |
| LMArena Korean | 1370 | — |
Instruction Following Step 5 Preview leads
o3: 72.8 (#127), Step 5 Preview: 76.0 (#50)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1368 | 1444 |
| IFEval | 86.9% | — |
Long Context o3 leads
o3: 53.3 (#6), Step 5 Preview: 44.5 (#64)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1372 | 1455 |
| Fiction.LiveBench | 88.9% | — |
| CL-bench | 17.8% | — |
Writing & Preference Too close to call
o3: 63.5 (#64), Step 5 Preview: 62.8 (#71)
| Benchmark | o3 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1410 | 1442 |
| LMArena Creative Writing | 1359 | 1410 |
| LMArena Multi-Turn | 1405 | 1447 |
| Short-Story Creative Writing | 83.9% | — |
| EQ-Bench Creative Writing | 1676 | — |
| WildBench | 86.1% | — |
Frequently asked questions
Is o3 better than Step 5 Preview?
o3 and Step 5 Preview score almost the same on the Noometry Index (47.5 vs 47.9), so choose on price, context window or the category you care about most.
Which is cheaper, o3 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 lists at $2 and $8.
Is o3 or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 46.8 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 and Step 5 Preview share?
15 benchmarks have published results for both models. o3 has 63 scored results on Noometry and Step 5 Preview has 18.