# Gemma 2 27B vs GPT-4

> Gemma 2 27B and GPT-4 score almost the same on the Noometry Index (29.4 vs 29.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemma-2-27b-vs-gpt-4
- Last updated: 2026-10-11
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. Gemma 2 27B scores higher in 3 categories and GPT-4 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 2 27B leads 44.2 to 34.9.
- The biggest single-benchmark swing is DTBench: 48% for Gemma 2 27B and 62.7% for GPT-4.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $30 / $60 for GPT-4.
- Gemma 2 27B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 27B | GPT-4 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 29.4 | 29.1 |
| Rank | 312 | 316 |
| Context | 8K | 8K |
| Input $/M | $0.65 | $30 |
| Output $/M | $0.65 | $60 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 27B: 34.1 (#246)
- GPT-4: 31.6 (#283)

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| BigCodeBench Instruct | 42.8% | 46% |
| LMArena Coding | 1211 | 1254 |
| BigCodeBench Complete | 52.5% | 57.2% |
| WeirdML | — | 12.4% |
| LiveBench Coding | 36% | — |
| HumanEval+ | — | 79.3% |

## Agentic & Tool Use

- Gemma 2 27B: —
- GPT-4: —

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| METR Time Horizons | — | 36.1% |

## Reasoning

- Gemma 2 27B: 15.3 (#315)
- GPT-4: 17.8 (#289)

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1241 |
| DTBench | 48% | 62.7% |
| LMCA | 7.1% | 17.1% |
| Epoch Capabilities Index | 122.08 | 125.89 |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 28.1% | — |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | 47.9% | — |
| BIG-Bench Hard | — | 75.1% |
| ForecastBench | — | 57.8 |
| HellaSwag | — | 95.3% |
| LiveBench | 38.2% | — |
| WinoGrande | — | 87.5% |

## Math

- Gemma 2 27B: 10.7 (#311)
- GPT-4: 10.8 (#309)

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.4% | 1.1% |
| LMArena Math | 1212 | 1269 |
| MATH Level 5 | 27.9% | 23% |
| LiveBench Math | 26.5% | — |
| GSM8K | — | 92% |

## Knowledge

- Gemma 2 27B: 19.0 (#280)
- GPT-4: 18.4 (#282)

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| GPQA Diamond | 36.5% | 35.7% |
| LMArena Expert | 1172 | 1211 |
| MMLU | 75.7% | 86.4% |
| Confabulations | 27.1% | — |
| TriviaQA | — | 84.8% |

## Multilingual

- Gemma 2 27B: 38.6 (#226)
- GPT-4: 40.6 (#215)

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| LMArena Non-English | 1217 | 1246 |
| LMArena Chinese | 1221 | 1242 |
| LMArena French | 1247 | 1283 |
| LMArena German | 1209 | 1251 |
| LMArena Japanese | 1175 | 1209 |
| LMArena Korean | 1174 | 1184 |
| LMArena Russian | 1234 | 1251 |
| LMArena Spanish | 1228 | 1261 |

## Instruction Following

- Gemma 2 27B: 60.5 (#249)
- GPT-4: 65.3 (#222)

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1206 | 1241 |
| LiveBench Instruction Following | 58.1% | — |

## Long Context

- Gemma 2 27B: 37.3 (#218)
- GPT-4: 37.7 (#212)

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| LMArena Longer Query | 1231 | 1244 |

## Writing & Preference

- Gemma 2 27B: 44.2 (#225)
- GPT-4: 34.9 (#268)

| Benchmark | Gemma 2 27B | GPT-4 |
|---|---|---|
| LMArena Text | 1231 | 1263 |
| LMArena Creative Writing | 1241 | 1244 |
| LMArena Multi-Turn | 1224 | 1257 |
| EQ-Bench Creative Writing | — | 752 |
| LiveBench Language | 32.6% | — |

## FAQ

### Is Gemma 2 27B better than GPT-4?

Gemma 2 27B and GPT-4 score almost the same on the Noometry Index (29.4 vs 29.1), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemma 2 27B or GPT-4?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; GPT-4 lists at $30 and $60.

### Is Gemma 2 27B or GPT-4 better for coding?

Gemma 2 27B scores higher on coding benchmarks: 34.1 versus 31.6 in the Noometry coding category.

### Which has the bigger context window?

Both accept 8K tokens.

### How many benchmarks do Gemma 2 27B and GPT-4 share?

26 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and GPT-4 has 38.