Model comparison
Gemma 3n E4b IT vs GPT-5 Nano
Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 33.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 5 categories and GPT-5 Nano in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3n E4b IT leads 50.3 to 39.4.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 31.5% for Gemma 3n E4b IT and 62.2% for GPT-5 Nano.
- Gemma 3n E4b IT is cheaper at $0.06 / $0.12 per million input/output tokens, against $0.05 / $0.40 for GPT-5 Nano.
- GPT-5 Nano accepts more context: 400K tokens versus 33K.
- Gemma 3n E4b IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 3n E4b IT | GPT-5 Nano | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 36.7 | 33.4 |
| Released | 2025-05-20 | 2025-08-07 |
| Weights | Open | Proprietary |
| Context window | 33K | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.06 | $0.05 |
| Output $ / M tokens | $0.12 | $0.40 |
| Results tracked | 18 | 48 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3n E4b IT leads
Gemma 3n E4b IT: 36.4 (#193), GPT-5 Nano: 33.3 (#248)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| LMArena Coding | 1269 | 1351 |
| SWE-bench Verified (bash only) | — | 34.8% |
| WeirdML | — | 38.1% |
| ALE-Bench | — | 718.67 |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, GPT-5 Nano: 25.6 (#99)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| Terminal-Bench | — | 21.8% |
| Berkeley Function Calling Leaderboard | — | 51.5% |
Reasoning Gemma 3n E4b IT leads
Gemma 3n E4b IT: 19.2 (#239), GPT-5 Nano: 16.4 (#291)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 62.2% |
| LMArena Hard Prompts | 1284 | 1329 |
| ARC-AGI-2 | — | 2.6% |
| ARC-AGI-1 | — | 20.7% |
| Chess Puzzles | — | 27% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 62.7% |
| LMCA | — | 7.9% |
| Epoch Capabilities Index | — | 139.39 |
| ForecastBench | — | 59.1 |
Math Gemma 3n E4b IT leads
Gemma 3n E4b IT: 32.5 (#186), GPT-5 Nano: 29.1 (#221)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| LMArena Math | 1251 | 1318 |
| FrontierMath (Tiers 1-3) | — | 20% |
| FrontierMath Tier 4 | — | 2.4% |
| OTIS Mock AIME 2024-2025 | — | 81.1% |
| ProofBench | — | 12% |
| Omni-MATH | — | 54.6% |
| MATH Level 5 | — | 95.2% |
| FrontierMath (Feb 2025 set) | — | 8.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GPT-5 Nano leads
Gemma 3n E4b IT: 33.6 (#193), GPT-5 Nano: 35.8 (#166)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| LMArena Expert | 1245 | 1321 |
| GPQA Diamond | — | 69.4% |
| SimpleQA Verified | — | 11.7% |
| MMLU-Pro | — | 77.8% |
| Vectara Hallucination Rate | — | 10.5% |
| GPQA (HELM) | — | 67.9% |
Multimodal Not comparable
Gemma 3n E4b IT: —, GPT-5 Nano: 30.7 (#102)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| LMArena Vision | — | 1159 |
| VPCT | — | 37.2% |
Multilingual GPT-5 Nano leads
Gemma 3n E4b IT: 43.5 (#179), GPT-5 Nano: 45.5 (#167)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| LMArena Non-English | 1285 | 1313 |
| LMArena Chinese | 1310 | 1355 |
| LMArena German | 1312 | 1329 |
| LMArena Korean | 1259 | 1269 |
| LMArena Russian | 1288 | 1296 |
| LMArena Spanish | 1305 | 1360 |
| LMArena French | 1330 | — |
| LMArena Japanese | 1274 | — |
Instruction Following GPT-5 Nano leads
Gemma 3n E4b IT: 66.3 (#205), GPT-5 Nano: 75.2 (#72)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| LMArena Instruction Following | 1255 | 1306 |
| IFEval | — | 93.2% |
Long Context Gemma 3n E4b IT leads
Gemma 3n E4b IT: 38.8 (#185), GPT-5 Nano: 31.3 (#275)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| LMArena Longer Query | 1277 | 1313 |
| Fiction.LiveBench | — | 44.4% |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.3 (#181), GPT-5 Nano: 39.4 (#244)
| Benchmark | Gemma 3n E4b IT | GPT-5 Nano |
|---|---|---|
| LMArena Text | 1306 | 1320 |
| LMArena Creative Writing | 1287 | 1250 |
| LMArena Multi-Turn | 1276 | 1311 |
| EQ-Bench Creative Writing | — | 705 |
| WildBench | — | 80.6% |
Frequently asked questions
Is Gemma 3n E4b IT better than GPT-5 Nano?
Gemma 3n E4b IT is the stronger model overall, scoring 36.7 to 33.4 on the Noometry Index.
Which is cheaper, Gemma 3n E4b IT or GPT-5 Nano?
Gemma 3n E4b IT is cheaper. It lists at $0.06 per million input tokens and $0.12 per million output tokens; GPT-5 Nano lists at $0.05 and $0.40.
Is Gemma 3n E4b IT or GPT-5 Nano better for coding?
Gemma 3n E4b IT scores higher on coding benchmarks: 36.4 versus 33.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Nano does, with 400K tokens against 33K.
How many benchmarks do Gemma 3n E4b IT and GPT-5 Nano share?
16 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and GPT-5 Nano has 48.