Model comparison
Gemma 3n E4b IT vs GPT-5.3 Codex
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 37.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
GoogleSummary
- The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 37.0.
- Gemma 3n E4b IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 3n E4b IT | GPT-5.3 Codex | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.3 | 45.8 |
| Released | — | 2026-02-05 |
| Weights | Open | Proprietary |
| Context window | — | 400K |
| Max output | — | 128K |
| Input $ / M tokens | — | $1.75 |
| Output $ / M tokens | — | $14 |
| Results tracked | 18 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
Gemma 3n E4b IT: 37.0 (#198), GPT-5.3 Codex: 48.6 (#56)
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| SWE-bench Verified | — | 74.8% |
| LMArena WebDev | — | 1409 |
| WeirdML | — | 79.3% |
| LMArena Coding | 1268 | — |
| ALE-Bench | — | 1,655 |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, GPT-5.3 Codex: 48.0 (#9)
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| Terminal-Bench | — | 78.4% |
| METR Time Horizons | — | 74.5% |
| Vending-Bench 2 | — | 5,940 |
Reasoning Not comparable
Gemma 3n E4b IT: 19.9 (#247), GPT-5.3 Codex: —
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | — |
| LMArena Hard Prompts | 1284 | — |
| Epoch Capabilities Index | — | 156.77 |
Math Not comparable
Gemma 3n E4b IT: 35.1 (#188), GPT-5.3 Codex: —
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Math | 1251 | — |
Knowledge Not comparable
Gemma 3n E4b IT: 34.2 (#198), GPT-5.3 Codex: —
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Expert | 1246 | — |
Multilingual Not comparable
Gemma 3n E4b IT: 43.4 (#183), GPT-5.3 Codex: —
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1285 | — |
| LMArena Chinese | 1309 | — |
| LMArena French | 1330 | — |
| LMArena German | 1311 | — |
| LMArena Japanese | 1272 | — |
| LMArena Korean | 1259 | — |
| LMArena Russian | 1288 | — |
| LMArena Spanish | 1305 | — |
Instruction Following Not comparable
Gemma 3n E4b IT: 66.1 (#210), GPT-5.3 Codex: —
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Instruction Following | 1255 | — |
Long Context Not comparable
Gemma 3n E4b IT: 38.7 (#191), GPT-5.3 Codex: —
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1276 | — |
Writing & Preference Not comparable
Gemma 3n E4b IT: 50.1 (#186), GPT-5.3 Codex: —
| Benchmark | Gemma 3n E4b IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1306 | — |
| LMArena Creative Writing | 1287 | — |
| LMArena Multi-Turn | 1276 | — |
Frequently asked questions
Is Gemma 3n E4b IT better than GPT-5.3 Codex?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 37.3 on the Noometry Index.
Is Gemma 3n E4b IT or GPT-5.3 Codex better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 37.0 in the Noometry coding category.
How many benchmarks do Gemma 3n E4b IT and GPT-5.3 Codex share?
0 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and GPT-5.3 Codex has 8.