Model comparison
GPT-4o mini vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 25.5 on the Noometry Index. GPT-4o mini costs 5.4× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
StepFunSummary
- They share 14 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Step 5 Preview in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 10.4.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 128K.
Side by side
| GPT-4o mini | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 25.5 | 47.9 |
| Released | 2024-07-18 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 1.02M |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.15 | $1 |
| Output $ / M tokens | $0.60 | $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
GPT-4o mini: 22.0 (#335), Step 5 Preview: 51.8 (#36)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1290 | 1480 |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Step 5 Preview: —
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Step 5 Preview leads
GPT-4o mini: 8.7 (#347), Step 5 Preview: 40.0 (#57)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1465 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| CritPt | — | 20.9% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Epoch Capabilities Index | 126.56 | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Step 5 Preview leads
GPT-4o mini: 10.4 (#314), Step 5 Preview: 46.1 (#72)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Math | 1267 | 1470 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| ProofBench | — | 42% |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge Step 5 Preview leads
GPT-4o mini: 17.7 (#284), Step 5 Preview: 41.2 (#112)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1235 | 1470 |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Step 5 Preview leads
GPT-4o mini: 25.9 (#122), Step 5 Preview: 41.0 (#41)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1066 | 1267 |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Step 5 Preview leads
GPT-4o mini: 42.0 (#199), Step 5 Preview: 53.8 (#54)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1266 | 1432 |
| LMArena Chinese | 1265 | 1519 |
| LMArena Russian | 1275 | 1436 |
| LMArena Spanish | 1276 | 1439 |
| LMArena French | 1297 | — |
| LMArena German | 1272 | — |
| LMArena Japanese | 1216 | — |
| LMArena Korean | 1195 | — |
Instruction Following Step 5 Preview leads
GPT-4o mini: 61.9 (#239), Step 5 Preview: 76.0 (#50)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1258 | 1444 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Step 5 Preview leads
GPT-4o mini: 39.1 (#186), Step 5 Preview: 44.5 (#64)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1289 | 1455 |
Writing & Preference Step 5 Preview leads
GPT-4o mini: 39.5 (#248), Step 5 Preview: 62.8 (#71)
| Benchmark | GPT-4o mini | Step 5 Preview |
|---|---|---|
| LMArena Text | 1286 | 1442 |
| LMArena Creative Writing | 1268 | 1410 |
| LMArena Multi-Turn | 1285 | 1447 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 25.5 on the Noometry Index. GPT-4o mini costs 5.4× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or Step 5 Preview?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is GPT-4o mini or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 128K.
How many benchmarks do GPT-4o mini and Step 5 Preview share?
14 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Step 5 Preview has 18.