# Gemma 2 27B vs gpt-oss-20b

> gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-27b-vs-gpt-oss-20b
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemma 2 27B scores higher in 1 category and gpt-oss-20b in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 37.6 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 1.4% for Gemma 2 27B and 65.3% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- gpt-oss-20b accepts more context: 131K tokens versus 8K.

## Snapshot

| | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 29.2 | 32.1 |
| Rank | 302 | 249 |
| Context | 8K | 131K |
| Input $/M | $0.65 | $0.018 |
| Output $/M | $0.65 | $0.09 |
| Weights | Open | Open |

## Coding

- Gemma 2 27B: 33.5 (#243)
- gpt-oss-20b: 37.1 (#185)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| LMArena Coding | 1211 | 1307 |
| SciCode | — | 34.4% |
| WeirdML | — | 40.9% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | — | 566.05 |

## Agentic & Tool Use

- Gemma 2 27B: —
- gpt-oss-20b: 9.2 (#146)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |

## Reasoning

- Gemma 2 27B: 14.8 (#313)
- gpt-oss-20b: 18.8 (#251)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| LMArena Hard Prompts | 1199 | 1274 |
| DTBench | 48% | 68% |
| LMCA | 7.1% | 14.5% |
| Epoch Capabilities Index | 122.06 | 137.81 |
| Kagi LLM Benchmark | — | 53.2% |
| CritPt | — | 1.4% |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 28.1% | — |
| LiveBench Data Analysis | 47.9% | — |
| LiveBench | 38.2% | — |

## Math

- Gemma 2 27B: 10.0 (#306)
- gpt-oss-20b: 37.6 (#93)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 65.3% |
| LMArena Math | 1212 | 1317 |
| Omni-MATH | — | 56.5% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |

## Knowledge

- Gemma 2 27B: 18.9 (#275)
- gpt-oss-20b: 34.6 (#186)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 36.5% | 60.8% |
| LMArena Expert | 1172 | 1258 |
| MMLU-Pro | — | 74% |
| Confabulations | 27.1% | — |
| GPQA (HELM) | — | 59.4% |
| MMLU | 75.7% | — |

## Multilingual

- Gemma 2 27B: 38.8 (#221)
- gpt-oss-20b: 42.4 (#192)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1217 | 1269 |
| LMArena Chinese | 1221 | 1311 |
| LMArena German | 1209 | 1249 |
| LMArena Japanese | 1175 | 1245 |
| LMArena Korean | 1174 | 1239 |
| LMArena Russian | 1234 | 1279 |
| LMArena Spanish | 1228 | 1267 |
| LMArena French | 1246 | — |

## Instruction Following

- Gemma 2 27B: 60.7 (#244)
- gpt-oss-20b: 62.0 (#235)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1206 | 1236 |
| LiveBench Instruction Following | 58.1% | — |
| IFEval | — | 73.2% |

## Long Context

- Gemma 2 27B: 37.3 (#213)
- gpt-oss-20b: 37.9 (#203)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1231 | 1251 |

## Writing & Preference

- Gemma 2 27B: 44.4 (#220)
- gpt-oss-20b: 35.8 (#260)

| Benchmark | Gemma 2 27B | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1231 | 1288 |
| LMArena Creative Writing | 1241 | 1201 |
| LMArena Multi-Turn | 1224 | 1268 |
| EQ-Bench Creative Writing | — | 666 |
| WildBench | — | 73.7% |
| LiveBench Language | 32.6% | — |

## FAQ

### Is Gemma 2 27B better than gpt-oss-20b?

gpt-oss-20b is the stronger model overall, scoring 32.1 to 29.2 on the Noometry Index.

### Which is cheaper, Gemma 2 27B or gpt-oss-20b?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.

### Is Gemma 2 27B or gpt-oss-20b better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.1 versus 33.5 in the Noometry coding category.

### Which has the bigger context window?

gpt-oss-20b does, with 131K tokens against 8K.

### How many benchmarks do Gemma 2 27B and gpt-oss-20b share?

21 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and gpt-oss-20b has 34.