Model comparison
o4-mini vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 41.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. o4-mini scores higher in 2 categories and Step 5 Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 24.6.
- The biggest single-benchmark swing is CritPt: 0.6% for o4-mini and 20.9% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Step 5 Preview accepts more context: 1.02M tokens versus 200K.
Side by side
| o4-mini | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 41.6 | 47.9 |
| Released | 2025-04-16 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1.02M |
| Max output | 100K | 66K |
| Input $ / M tokens | $1.10 | $1 |
| Output $ / M tokens | $4.40 | $2.70 |
| Results tracked | 60 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
o4-mini: 40.9 (#127), Step 5 Preview: 51.8 (#36)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1368 | 1480 |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| CadEval | 62% | — |
| ALE-Bench | 826.17 | — |
| AlgoTune | 1.72 | — |
Agentic & Tool Use Not comparable
o4-mini: 32.6 (#61), Step 5 Preview: —
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| METR Time Horizons | 63.9% | — |
Reasoning Step 5 Preview leads
o4-mini: 24.6 (#162), Step 5 Preview: 40.0 (#57)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| CritPt | 0.6% | 20.9% |
| LMArena Hard Prompts | 1351 | 1465 |
| ARC-AGI-2 | 6.1% | — |
| SimpleBench | 38.7% | — |
| Kagi LLM Benchmark | 67.6% | — |
| ARC-AGI-1 | 58.7% | — |
| Chess Puzzles | 26% | — |
| EnigmaEval | 9.2% | — |
| Mystery Game Puzzles | 5% | — |
| DTBench | 77.6% | — |
| LMCA | 26.5% | — |
| Epoch Capabilities Index | 145.64 | — |
| ForecastBench | 61.8 | — |
Math Step 5 Preview leads
o4-mini: 40.8 (#89), Step 5 Preview: 46.1 (#72)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| LMArena Math | 1389 | 1470 |
| FrontierMath (Tiers 1-3) | 36.1% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 81.7% | — |
| ProofBench | — | 42% |
| Omni-MATH | 72% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 24.8% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge o4-mini leads
o4-mini: 43.6 (#91), Step 5 Preview: 41.2 (#112)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1343 | 1470 |
| GPQA Diamond | 79.6% | — |
| Humanity's Last Exam | 18.1% | — |
| SimpleQA Verified | 19.6% | — |
| MMLU-Pro | 82% | — |
| Confabulations | 15.8% | — |
| Vectara Hallucination Rate | 18.6% | — |
| GPQA (HELM) | 73.5% | — |
Multimodal Too close to call
o4-mini: 40.2 (#49), Step 5 Preview: 41.0 (#41)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1194 | 1267 |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |
Multilingual Step 5 Preview leads
o4-mini: 47.0 (#154), Step 5 Preview: 53.8 (#54)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1337 | 1432 |
| LMArena Chinese | 1354 | 1519 |
| LMArena Russian | 1334 | 1436 |
| LMArena Spanish | 1347 | 1439 |
| LMArena French | 1364 | — |
| LMArena German | 1336 | — |
| LMArena Japanese | 1308 | — |
| LMArena Korean | 1312 | — |
Instruction Following Too close to call
o4-mini: 75.2 (#68), Step 5 Preview: 76.0 (#50)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1321 | 1444 |
| IFEval | 92.8% | — |
Long Context o4-mini leads
o4-mini: 45.5 (#33), Step 5 Preview: 44.5 (#64)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1315 | 1455 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Step 5 Preview leads
o4-mini: 54.0 (#152), Step 5 Preview: 62.8 (#71)
| Benchmark | o4-mini | Step 5 Preview |
|---|---|---|
| LMArena Text | 1353 | 1442 |
| LMArena Creative Writing | 1294 | 1410 |
| LMArena Multi-Turn | 1350 | 1447 |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |
Frequently asked questions
Is o4-mini better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 41.6 on the Noometry Index.
Which is cheaper, o4-mini or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is o4-mini or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 40.9 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 o4-mini and Step 5 Preview share?
15 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Step 5 Preview has 18.