# Gemma 3n E4b IT vs GPT-4.1 nano

> Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 27.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3n-e4b-it-vs-gpt-4-1-nano
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 7 categories and GPT-4.1 nano in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemma 3n E4b IT leads 38.8 to 23.7.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $0.10 / $0.40 for GPT-4.1 nano.
- GPT-4.1 nano accepts more context: 1.05M tokens versus 33K.
- Gemma 3n E4b IT has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 36.7 | 27.7 |
| Rank | 203 | 322 |
| Context | 33K | 1.05M |
| Input $/M | $0.06 | $0.10 |
| Output $/M | $0.12 | $0.40 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3n E4b IT: 36.4 (#193)
- GPT-4.1 nano: 23.8 (#325)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| LMArena Coding | 1269 | 1306 |
| Aider Polyglot | — | 8.9% |
| SciCode | — | 25.9% |
| WeirdML | — | 19% |

## Agentic & Tool Use

- Gemma 3n E4b IT: —
- GPT-4.1 nano: 26.3 (#98)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 33% |

## Reasoning

- Gemma 3n E4b IT: 19.2 (#239)
- GPT-4.1 nano: 8.6 (#344)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 33.3% |
| LMArena Hard Prompts | 1284 | 1286 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 0% |
| CritPt | — | 0% |
| DTBench | — | 52.5% |
| LMCA | — | 5.5% |
| Epoch Capabilities Index | — | 129.62 |

## Math

- Gemma 3n E4b IT: 32.5 (#186)
- GPT-4.1 nano: 25.5 (#246)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| LMArena Math | 1251 | 1274 |
| OTIS Mock AIME 2024-2025 | — | 28.9% |
| Omni-MATH | — | 36.7% |
| MATH Level 5 | — | 70% |
| FrontierMath (Feb 2025 set) | — | 1% |

## Knowledge

- Gemma 3n E4b IT: 33.6 (#193)
- GPT-4.1 nano: 21.8 (#268)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| LMArena Expert | 1245 | 1272 |
| GPQA Diamond | — | 48.9% |
| SimpleQA Verified | — | 6% |
| MMLU-Pro | — | 55% |
| GPQA (HELM) | — | 50.7% |

## Multimodal

- Gemma 3n E4b IT: —
- GPT-4.1 nano: 28.6 (#108)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | — | 1063 |

## Multilingual

- Gemma 3n E4b IT: 43.5 (#179)
- GPT-4.1 nano: 41.8 (#200)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1285 | 1260 |
| LMArena Chinese | 1310 | 1270 |
| LMArena German | 1312 | 1288 |
| LMArena Japanese | 1274 | 1199 |
| LMArena Russian | 1288 | 1261 |
| LMArena French | 1330 | — |
| LMArena Korean | 1259 | — |
| LMArena Spanish | 1305 | — |

## Instruction Following

- Gemma 3n E4b IT: 66.3 (#205)
- GPT-4.1 nano: 68.0 (#188)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| LMArena Instruction Following | 1255 | 1267 |
| IFEval | — | 84.3% |

## Long Context

- Gemma 3n E4b IT: 38.8 (#185)
- GPT-4.1 nano: 23.7 (#291)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| LMArena Longer Query | 1277 | 1283 |
| Fiction.LiveBench | — | 25% |

## Writing & Preference

- Gemma 3n E4b IT: 50.3 (#181)
- GPT-4.1 nano: 40.7 (#238)

| Benchmark | Gemma 3n E4b IT | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1306 | 1285 |
| LMArena Creative Writing | 1287 | 1260 |
| LMArena Multi-Turn | 1276 | 1277 |
| EQ-Bench Creative Writing | — | 946 |
| WildBench | — | 81.2% |

## FAQ

### Is Gemma 3n E4b IT better than GPT-4.1 nano?

Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 27.7 on the Noometry Index.

### Which is cheaper, Gemma 3n E4b IT or GPT-4.1 nano?

Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; GPT-4.1 nano lists at $0.10 and $0.40.

### Is Gemma 3n E4b IT or GPT-4.1 nano better for coding?

Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 23.8 in the Noometry coding category.

### Which has the bigger context window?

GPT-4.1 nano does, with 1.05M tokens against 33K.

### How many benchmarks do Gemma 3n E4b IT and GPT-4.1 nano share?

15 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and GPT-4.1 nano has 38.