Model comparison
Gemma 3 4B vs GPT-4.1 nano
Gemma 3 4B and GPT-4.1 nano score almost the same on the Noometry Index (28.1 vs 27.9), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
GoogleSummary
- They share 20 benchmarks with published results for both. Gemma 3 4B scores higher in 5 categories and GPT-4.1 nano in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemma 3 4B leads 38.7 to 23.7.
- The biggest single-benchmark swing is GPQA Diamond: 23.2% for Gemma 3 4B and 48.9% for GPT-4.1 nano.
- Gemma 3 4B is cheaper at $0.04 / $0.08 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 131K.
- Gemma 3 4B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 4B | GPT-4.1 nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 28.1 | 27.9 |
| Released | 2025-03-12 | 2025-04-14 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 4K | 33K |
| Input $ / M tokens | $0.04 | $0.10 |
| Output $ / M tokens | $0.08 | $0.40 |
| Results tracked | 22 | 38 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 4B leads
Gemma 3 4B: 35.9 (#215), GPT-4.1 nano: 24.1 (#330)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| LMArena Coding | 1230 | 1306 |
| Aider Polyglot | — | 8.9% |
| SciCode | — | 25.9% |
| WeirdML | — | 19% |
Agentic & Tool Use GPT-4.1 nano leads
Gemma 3 4B: 20.9 (#142), GPT-4.1 nano: 26.5 (#104)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | 33% |
Reasoning Gemma 3 4B leads
Gemma 3 4B: 13.2 (#335), GPT-4.1 nano: 8.5 (#349)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 33.3% |
| LMArena Hard Prompts | 1253 | 1286 |
| DTBench | 50.9% | 52.5% |
| LMCA | 2.8% | 5.5% |
| Epoch Capabilities Index | 116.02 | 129.62 |
| ARC-AGI-2 | — | 0% |
| ARC-AGI-1 | — | 0% |
| CritPt | — | 0% |
| Chess Puzzles | 0% | — |
Math GPT-4.1 nano leads
Gemma 3 4B: 16.8 (#292), GPT-4.1 nano: 26.9 (#252)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 28.9% |
| LMArena Math | 1239 | 1274 |
| Omni-MATH | — | 36.7% |
| MATH Level 5 | — | 70% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge GPT-4.1 nano leads
Gemma 3 4B: 11.8 (#299), GPT-4.1 nano: 21.8 (#273)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| GPQA Diamond | 23.2% | 48.9% |
| LMArena Expert | 1223 | 1272 |
| SimpleQA Verified | — | 6% |
| MMLU-Pro | — | 55% |
| Vectara Hallucination Rate | 6.4% | — |
| GPQA (HELM) | — | 50.7% |
Multimodal Not comparable
Gemma 3 4B: —, GPT-4.1 nano: 29.2 (#113)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| LMArena Vision | — | 1063 |
Multilingual Too close to call
Gemma 3 4B: 42.5 (#194), GPT-4.1 nano: 41.6 (#205)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| LMArena Non-English | 1273 | 1260 |
| LMArena German | 1281 | 1288 |
| LMArena Russian | 1294 | 1261 |
| LMArena Chinese | — | 1270 |
| LMArena Japanese | — | 1198 |
Instruction Following GPT-4.1 nano leads
Gemma 3 4B: 65.2 (#225), GPT-4.1 nano: 67.8 (#193)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| LMArena Instruction Following | 1239 | 1267 |
| IFEval | — | 84.3% |
Long Context Gemma 3 4B leads
Gemma 3 4B: 38.7 (#194), GPT-4.1 nano: 23.7 (#296)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| LMArena Longer Query | 1273 | 1283 |
| Fiction.LiveBench | — | 25% |
Writing & Preference Gemma 3 4B leads
Gemma 3 4B: 42.0 (#239), GPT-4.1 nano: 40.5 (#243)
| Benchmark | Gemma 3 4B | GPT-4.1 nano |
|---|---|---|
| LMArena Text | 1291 | 1285 |
| LMArena Creative Writing | 1271 | 1260 |
| EQ-Bench Creative Writing | 1068 | 946 |
| LMArena Multi-Turn | 1255 | 1277 |
| WildBench | — | 81.2% |
Frequently asked questions
Is Gemma 3 4B better than GPT-4.1 nano?
Gemma 3 4B and GPT-4.1 nano score almost the same on the Noometry Index (28.1 vs 27.9), so choose on price, context window or the category you care about most.
Which is cheaper, Gemma 3 4B or GPT-4.1 nano?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GPT-4.1 nano lists at $0.10 and $0.40.
Is Gemma 3 4B or GPT-4.1 nano better for coding?
Gemma 3 4B scores higher on coding benchmarks: 35.9 versus 24.1 in the Noometry coding category.
Which has the bigger context window?
GPT-4.1 nano does, with 1.05M tokens against 131K.
How many benchmarks do Gemma 3 4B and GPT-4.1 nano share?
20 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GPT-4.1 nano has 38.