Model comparison
Gemma 2B vs gpt-oss-20b
gpt-oss-20b is the stronger model overall, scoring 32.5 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and gpt-oss-20b in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where gpt-oss-20b leads 42.2 to 23.0.
Side by side
| Gemma 2B | gpt-oss-20b | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 29.6 | 32.5 |
| Released | 2024-02-21 | 2025-08-05 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.018 |
| Output $ / M tokens | — | $0.09 |
| Results tracked | 23 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding gpt-oss-20b leads
Gemma 2B: 29.4 (#305), gpt-oss-20b: 37.6 (#192)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1010 | 1306 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Agentic & Tool Use Not comparable
Gemma 2B: —, gpt-oss-20b: 9.3 (#154)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
Reasoning Too close to call
Gemma 2B: 18.8 (#275), gpt-oss-20b: 19.3 (#261)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 989 | 1274 |
| Epoch Capabilities Index | 94.2 | 137.82 |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| DTBench | — | 68% |
| LMCA | — | 14.5% |
| BIG-Bench Hard | 35.2% | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math gpt-oss-20b leads
Gemma 2B: 30.0 (#239), gpt-oss-20b: 39.4 (#103)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| LMArena Math | 1009 | 1317 |
| OTIS Mock AIME 2024-2025 | — | 65.3% |
| Omni-MATH | — | 56.5% |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, gpt-oss-20b: 34.6 (#195)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | — | 60.8% |
| MMLU-Pro | — | 74% |
| GPQA (HELM) | — | 59.4% |
| LMArena Expert | — | 1258 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual gpt-oss-20b leads
Gemma 2B: 23.0 (#294), gpt-oss-20b: 42.2 (#197)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 958 | 1268 |
| LMArena Chinese | 986 | 1314 |
| LMArena Russian | 937 | 1278 |
| LMArena German | — | 1255 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1236 |
| LMArena Spanish | — | 1267 |
Instruction Following gpt-oss-20b leads
Gemma 2B: 48.5 (#302), gpt-oss-20b: 61.8 (#240)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 970 | 1236 |
| IFEval | — | 73.2% |
Long Context gpt-oss-20b leads
Gemma 2B: 29.9 (#291), gpt-oss-20b: 37.9 (#209)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 981 | 1250 |
Writing & Preference gpt-oss-20b leads
Gemma 2B: 24.0 (#308), gpt-oss-20b: 35.5 (#265)
| Benchmark | Gemma 2B | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1002 | 1287 |
| LMArena Creative Writing | 987 | 1201 |
| LMArena Multi-Turn | 945 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
Frequently asked questions
Is Gemma 2B better than gpt-oss-20b?
gpt-oss-20b is the stronger model overall, scoring 32.5 to 29.6 on the Noometry Index.
Is Gemma 2B or gpt-oss-20b better for coding?
gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and gpt-oss-20b share?
12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and gpt-oss-20b has 34.