Model comparison
GPT-5 Nano vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 33.5 on the Noometry Index. GPT-5 Nano costs 10× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. GPT-5 Nano scores higher in 0 categories and Step 5 Preview in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 16.3.
- The biggest single-benchmark swing is ProofBench: 12% for GPT-5 Nano and 42% for Step 5 Preview.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 400K.
Side by side
| GPT-5 Nano | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 33.5 | 47.9 |
| Released | 2025-08-07 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 1.02M |
| Max output | 128K | 66K |
| Input $ / M tokens | $0.05 | $1 |
| Output $ / M tokens | $0.40 | $2.70 |
| Results tracked | 49 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
GPT-5 Nano: 33.6 (#254), Step 5 Preview: 51.8 (#36)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1351 | 1480 |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| WeirdML | 38.1% | — |
| ALE-Bench | 718.67 | — |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), Step 5 Preview: —
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning Step 5 Preview leads
GPT-5 Nano: 16.3 (#306), Step 5 Preview: 40.0 (#57)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1328 | 1465 |
| ARC-AGI-2 | 2.6% | — |
| Kagi LLM Benchmark | 62.2% | — |
| ARC-AGI-1 | 20.7% | — |
| CritPt | — | 20.9% |
| Chess Puzzles | 27% | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| Epoch Capabilities Index | 139.38 | — |
| ForecastBench | 59.1 | — |
Math Step 5 Preview leads
GPT-5 Nano: 29.4 (#241), Step 5 Preview: 46.1 (#72)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| ProofBench | 12% | 42% |
| LMArena Math | 1317 | 1470 |
| FrontierMath (Tiers 1-3) | 20% | — |
| FrontierMath Tier 4 | 2.4% | — |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| Omni-MATH | 54.6% | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Step 5 Preview leads
GPT-5 Nano: 35.9 (#178), Step 5 Preview: 41.2 (#112)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1321 | 1470 |
| GPQA Diamond | 69.4% | — |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
Multimodal Step 5 Preview leads
GPT-5 Nano: 31.3 (#108), Step 5 Preview: 41.0 (#41)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1159 | 1267 |
| VPCT | 37.2% | — |
Multilingual Step 5 Preview leads
GPT-5 Nano: 45.3 (#172), Step 5 Preview: 53.8 (#54)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1313 | 1432 |
| LMArena Chinese | 1356 | 1519 |
| LMArena Russian | 1296 | 1436 |
| LMArena Spanish | 1360 | 1439 |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
Instruction Following Too close to call
GPT-5 Nano: 75.0 (#79), Step 5 Preview: 76.0 (#50)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1306 | 1444 |
| IFEval | 93.2% | — |
Long Context Step 5 Preview leads
GPT-5 Nano: 31.3 (#281), Step 5 Preview: 44.5 (#64)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1312 | 1455 |
| Fiction.LiveBench | 44.4% | — |
Writing & Preference Step 5 Preview leads
GPT-5 Nano: 39.1 (#249), Step 5 Preview: 62.8 (#71)
| Benchmark | GPT-5 Nano | Step 5 Preview |
|---|---|---|
| LMArena Text | 1320 | 1442 |
| LMArena Creative Writing | 1249 | 1410 |
| LMArena Multi-Turn | 1311 | 1447 |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
Frequently asked questions
Is GPT-5 Nano better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 33.5 on the Noometry Index. GPT-5 Nano costs 10× 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-5 Nano or Step 5 Preview?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; Step 5 Preview lists at $1 and $2.70.
Is GPT-5 Nano or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 400K.
How many benchmarks do GPT-5 Nano and Step 5 Preview share?
15 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and Step 5 Preview has 18.