Model comparison
GPT-4.1 nano vs Step 3.7 Flash
Step 3.7 Flash is the stronger model overall, scoring 37.3 to 27.9 on the Noometry Index. GPT-4.1 nano costs 2.4× less per token, which makes it the better buy when Step 3.7 Flash's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
StepFunSummary
- They share 2 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and Step 3.7 Flash in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.7 Flash leads 42.9 to 26.9.
- The biggest single-benchmark swing is SciCode: 25.9% for GPT-4.1 nano and 40% for Step 3.7 Flash.
- GPT-4.1 nano is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 256K.
- Step 3.7 Flash has downloadable open weights; the other is API-only.
Side by side
| GPT-4.1 nano | Step 3.7 Flash | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 27.9 | 37.3 |
| Released | 2025-04-14 | 2026-05-29 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 256K |
| Max output | 33K | 256K |
| Input $ / M tokens | $0.10 | $0.18 |
| Output $ / M tokens | $0.40 | $1.11 |
| Results tracked | 38 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.7 Flash leads
GPT-4.1 nano: 24.1 (#330), Step 3.7 Flash: 40.0 (#150)
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| SciCode | 25.9% | 40% |
| Aider Polyglot | 8.9% | — |
| WeirdML | 19% | — |
| LMArena Coding | 1306 | — |
| ALE-Bench | — | 694.12 |
Agentic & Tool Use Not comparable
GPT-4.1 nano: 26.5 (#104), Step 3.7 Flash: —
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |
Reasoning Step 3.7 Flash leads
GPT-4.1 nano: 8.5 (#349), Step 3.7 Flash: 21.6 (#219)
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| CritPt | 0% | 2.3% |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 33.3% | — |
| NYT Connections (extended) | — | 39.7% |
| ARC-AGI-1 | 0% | — |
| LMArena Hard Prompts | 1286 | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 129.62 | — |
Math Step 3.7 Flash leads
GPT-4.1 nano: 26.9 (#252), Step 3.7 Flash: 42.9 (#82)
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 28.9% | — |
| Omni-MATH | 36.7% | — |
| LMArena Math | 1274 | — |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |
Knowledge Not comparable
GPT-4.1 nano: 21.8 (#273), Step 3.7 Flash: —
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 48.9% | — |
| SimpleQA Verified | 6% | — |
| MMLU-Pro | 55% | — |
| GPQA (HELM) | 50.7% | — |
| LMArena Expert | 1272 | — |
Multimodal Not comparable
GPT-4.1 nano: 29.2 (#113), Step 3.7 Flash: —
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| LMArena Vision | 1063 | — |
Multilingual Not comparable
GPT-4.1 nano: 41.6 (#205), Step 3.7 Flash: —
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1260 | — |
| LMArena Chinese | 1270 | — |
| LMArena German | 1288 | — |
| LMArena Japanese | 1198 | — |
| LMArena Russian | 1261 | — |
Instruction Following Not comparable
GPT-4.1 nano: 67.8 (#193), Step 3.7 Flash: —
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| IFEval | 84.3% | — |
| LMArena Instruction Following | 1267 | — |
Long Context Not comparable
GPT-4.1 nano: 23.7 (#296), Step 3.7 Flash: —
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| Fiction.LiveBench | 25% | — |
| LMArena Longer Query | 1283 | — |
Writing & Preference Not comparable
GPT-4.1 nano: 40.5 (#243), Step 3.7 Flash: —
| Benchmark | GPT-4.1 nano | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1285 | — |
| LMArena Creative Writing | 1260 | — |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |
| LMArena Multi-Turn | 1277 | — |
Frequently asked questions
Is GPT-4.1 nano better than Step 3.7 Flash?
Step 3.7 Flash is the stronger model overall, scoring 37.3 to 27.9 on the Noometry Index. GPT-4.1 nano costs 2.4× less per token, which makes it the better buy when Step 3.7 Flash's lead doesn't matter for your workload.
Which is cheaper, GPT-4.1 nano or Step 3.7 Flash?
GPT-4.1 nano is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.
Is GPT-4.1 nano or Step 3.7 Flash better for coding?
Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 256K.
How many benchmarks do GPT-4.1 nano and Step 3.7 Flash share?
2 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Step 3.7 Flash has 5.