Model comparison
GPT-4.1 mini vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 33.6 on the Noometry Index. GPT-4.1 mini costs 2.0× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. GPT-4.1 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 reasoning, where Step 5 Preview leads 40.0 to 10.8.
- The biggest single-benchmark swing is CritPt: 0% for GPT-4.1 mini and 20.9% for Step 5 Preview.
- GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- GPT-4.1 mini accepts more context: 1.05M tokens versus 1.02M.
Side by side
| GPT-4.1 mini | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 33.6 | 47.9 |
| Released | 2025-04-14 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 1.02M |
| Max output | 33K | 66K |
| Input $ / M tokens | $0.40 | $1 |
| Output $ / M tokens | $1.60 | $2.70 |
| Results tracked | 47 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
GPT-4.1 mini: 30.6 (#293), Step 5 Preview: 51.8 (#36)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| SciCode | 40.4% | 58.9% |
| LMArena Coding | 1367 | 1480 |
| SWE-bench Verified (bash only) | 23.9% | — |
| Aider Polyglot | 32.4% | — |
| LMArena WebDev | — | 1564 |
| WeirdML | 37.6% | — |
| BigCodeBench Instruct | 48.9% | — |
| CadEval | 16% | — |
Agentic & Tool Use Not comparable
GPT-4.1 mini: 33.3 (#55), Step 5 Preview: —
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 50.5% | — |
Reasoning Step 5 Preview leads
GPT-4.1 mini: 10.8 (#340), Step 5 Preview: 40.0 (#57)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| CritPt | 0% | 20.9% |
| LMArena Hard Prompts | 1349 | 1465 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 48.6% | — |
| ARC-AGI-1 | 3.5% | — |
| Chess Puzzles | 7% | — |
| Mystery Game Puzzles | 7% | — |
| DTBench | 68.8% | — |
| LMCA | 21.1% | — |
| Epoch Capabilities Index | 135.01 | — |
Math Step 5 Preview leads
GPT-4.1 mini: 24.1 (#270), Step 5 Preview: 46.1 (#72)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| LMArena Math | 1343 | 1470 |
| FrontierMath (Tiers 1-3) | 6.7% | — |
| OTIS Mock AIME 2024-2025 | 44.7% | — |
| ProofBench | — | 42% |
| Omni-MATH | 49.1% | — |
| MATH Level 5 | 87.3% | — |
| FrontierMath (Feb 2025 set) | 4.5% | — |
Knowledge Step 5 Preview leads
GPT-4.1 mini: 34.7 (#194), Step 5 Preview: 41.2 (#112)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1338 | 1470 |
| GPQA Diamond | 65.8% | — |
| SimpleQA Verified | 12.7% | — |
| MMLU-Pro | 78.3% | — |
| GPQA (HELM) | 61.4% | — |
Multimodal Step 5 Preview leads
GPT-4.1 mini: 35.8 (#82), Step 5 Preview: 41.0 (#41)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1181 | 1267 |
Multilingual Step 5 Preview leads
GPT-4.1 mini: 45.7 (#166), Step 5 Preview: 53.8 (#54)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1318 | 1432 |
| LMArena Chinese | 1329 | 1519 |
| LMArena Russian | 1324 | 1436 |
| LMArena Spanish | 1319 | 1439 |
| LMArena French | 1358 | — |
| LMArena German | 1351 | — |
| LMArena Japanese | 1290 | — |
| LMArena Korean | 1298 | — |
Instruction Following Step 5 Preview leads
GPT-4.1 mini: 73.7 (#118), Step 5 Preview: 76.0 (#50)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1333 | 1444 |
| IFEval | 90.4% | — |
Long Context Step 5 Preview leads
GPT-4.1 mini: 31.8 (#275), Step 5 Preview: 44.5 (#64)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1344 | 1455 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Step 5 Preview leads
GPT-4.1 mini: 48.6 (#199), Step 5 Preview: 62.8 (#71)
| Benchmark | GPT-4.1 mini | Step 5 Preview |
|---|---|---|
| LMArena Text | 1340 | 1442 |
| LMArena Creative Writing | 1300 | 1410 |
| LMArena Multi-Turn | 1354 | 1447 |
| EQ-Bench Creative Writing | 1147 | — |
| WildBench | 83.8% | — |
Frequently asked questions
Is GPT-4.1 mini better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 33.6 on the Noometry Index. GPT-4.1 mini costs 2.0× 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-4.1 mini or Step 5 Preview?
GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is GPT-4.1 mini or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 30.6 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 mini does, with 1.05M tokens against 1.02M.
How many benchmarks do GPT-4.1 mini and Step 5 Preview share?
16 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Step 5 Preview has 18.