# GPT-4.1 nano vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 27.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-nano-vs-step-3
- Last updated: 2026-10-11
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. GPT-4.1 nano scores higher in 0 categories and Step 3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3 leads 28.4 to 8.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 33.3% for GPT-4.1 nano and 62.3% for Step 3.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.1 nano | Step 3 |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 27.9 | 40.5 |
| Rank | 327 | 149 |
| Context | 1.05M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.40 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4.1 nano: 24.1 (#330)
- Step 3: 40.1 (#147)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| LMArena Coding | 1306 | 1367 |
| Aider Polyglot | 8.9% | — |
| SciCode | 25.9% | — |
| WeirdML | 19% | — |

## Agentic & Tool Use

- GPT-4.1 nano: 26.5 (#104)
- Step 3: —

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |

## Reasoning

- GPT-4.1 nano: 8.5 (#349)
- Step 3: 28.4 (#105)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 33.3% | 62.3% |
| LMArena Hard Prompts | 1286 | 1355 |
| ARC-AGI-2 | 0% | — |
| ARC-AGI-1 | 0% | — |
| CritPt | 0% | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |
| Epoch Capabilities Index | 129.62 | — |

## Math

- GPT-4.1 nano: 26.9 (#252)
- Step 3: 37.6 (#148)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| LMArena Math | 1274 | 1366 |
| OTIS Mock AIME 2024-2025 | 28.9% | — |
| Omni-MATH | 36.7% | — |
| MATH Level 5 | 70% | — |
| FrontierMath (Feb 2025 set) | 1% | — |

## Knowledge

- GPT-4.1 nano: 21.8 (#273)
- Step 3: 36.8 (#164)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| LMArena Expert | 1272 | 1333 |
| GPQA Diamond | 48.9% | — |
| SimpleQA Verified | 6% | — |
| MMLU-Pro | 55% | — |
| GPQA (HELM) | 50.7% | — |

## Multimodal

- GPT-4.1 nano: 29.2 (#113)
- Step 3: 35.5 (#86)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| LMArena Vision | 1063 | 1177 |

## Multilingual

- GPT-4.1 nano: 41.6 (#205)
- Step 3: 46.3 (#159)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| LMArena Non-English | 1260 | 1327 |
| LMArena Chinese | 1270 | 1397 |
| LMArena German | 1288 | 1371 |
| LMArena Russian | 1261 | 1331 |
| LMArena Japanese | 1198 | — |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |

## Instruction Following

- GPT-4.1 nano: 67.8 (#193)
- Step 3: 70.4 (#164)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1267 | 1332 |
| IFEval | 84.3% | — |

## Long Context

- GPT-4.1 nano: 23.7 (#296)
- Step 3: 40.3 (#157)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| LMArena Longer Query | 1283 | 1326 |
| Fiction.LiveBench | 25% | — |

## Writing & Preference

- GPT-4.1 nano: 40.5 (#243)
- Step 3: 54.3 (#151)

| Benchmark | GPT-4.1 nano | Step 3 |
|---|---|---|
| LMArena Text | 1285 | 1350 |
| LMArena Creative Writing | 1260 | 1321 |
| LMArena Multi-Turn | 1277 | 1341 |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |

## FAQ

### Is GPT-4.1 nano better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 27.9 on the Noometry Index.

### Is GPT-4.1 nano or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 24.1 in the Noometry coding category.

### How many benchmarks do GPT-4.1 nano and Step 3 share?

15 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and Step 3 has 17.