Model comparison
Gemma 3n E4b IT vs gpt-oss-20b
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 32.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
GoogleSummary
- They share 17 benchmarks with published results for both. Gemma 3n E4b IT scores higher in 5 categories and gpt-oss-20b in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3n E4b IT leads 50.1 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 31.5% for Gemma 3n E4b IT and 53.2% for gpt-oss-20b.
Side by side
| Gemma 3n E4b IT | gpt-oss-20b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 37.3 | 32.5 |
| Released | — | 2025-08-05 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.018 |
| Output $ / M tokens | — | $0.09 |
| Results tracked | 18 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 3n E4b IT: 37.0 (#198), gpt-oss-20b: 37.6 (#192)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1268 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |
Agentic & Tool Use Not comparable
Gemma 3n E4b IT: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning Too close to call
Gemma 3n E4b IT: 19.9 (#247), gpt-oss-20b: 19.3 (#261)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| Kagi LLM Benchmark | 31.5% | 53.2% |
| LMArena Hard Prompts | 1284 | 1274 |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| Epoch Capabilities Index | — | 137.82 |
Math gpt-oss-20b leads
Gemma 3n E4b IT: 35.1 (#188), gpt-oss-20b: 39.4 (#103)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1251 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
Knowledge Too close to call
Gemma 3n E4b IT: 34.2 (#198), gpt-oss-20b: 34.6 (#195)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| LMArena Expert | 1246 | 1258 |
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
Multilingual Gemma 3n E4b IT leads
Gemma 3n E4b IT: 43.4 (#183), gpt-oss-20b: 42.2 (#197)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1285 | 1268 |
| LMArena Chinese | 1309 | 1314 |
| LMArena German | 1311 | 1255 |
| LMArena Japanese | 1272 | 1244 |
| LMArena Korean | 1259 | 1236 |
| LMArena Russian | 1288 | 1278 |
| LMArena Spanish | 1305 | 1267 |
| LMArena French | 1330 | — |
Instruction Following Gemma 3n E4b IT leads
Gemma 3n E4b IT: 66.1 (#210), gpt-oss-20b: 61.8 (#240)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1255 | 1236 |
| IFEval | — | 73.2% |
Long Context Too close to call
Gemma 3n E4b IT: 38.7 (#191), gpt-oss-20b: 37.9 (#209)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1276 | 1250 |
Writing & Preference Gemma 3n E4b IT leads
Gemma 3n E4b IT: 50.1 (#186), gpt-oss-20b: 35.5 (#265)
| Benchmark | Gemma 3n E4b IT | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1306 | 1287 |
| LMArena Creative Writing | 1287 | 1201 |
| LMArena Multi-Turn | 1276 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
Frequently asked questions
Is Gemma 3n E4b IT better than gpt-oss-20b?
Gemma 3n E4b IT is the stronger model overall, scoring 37.3 to 32.5 on the Noometry Index.
Is Gemma 3n E4b IT or gpt-oss-20b better for coding?
They score almost the same on coding (37.0 vs 37.6); test both on your own repository before choosing.
How many benchmarks do Gemma 3n E4b IT and gpt-oss-20b share?
17 benchmarks have published results for both models. Gemma 3n E4b IT has 18 scored results on Noometry and gpt-oss-20b has 34.