# Gemma 2 9B vs GPT-4 Turbo

> GPT-4 Turbo is the stronger model overall, scoring 30.5 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-gpt-4-turbo
- Last updated: 2026-10-12
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Gemma 2 9B scores higher in 2 categories and GPT-4 Turbo in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4 Turbo leads 47.7 to 32.1.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 46.7% for GPT-4 Turbo.
- Gemma 2 9B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 25.9 | 30.5 |
| Rank | 341 | 292 |
| Context | — | 128K |
| Input $/M | — | $10 |
| Output $/M | — | $30 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 9B: 29.4 (#304)
- GPT-4 Turbo: 33.8 (#249)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| BigCodeBench Instruct | 34.7% | 48.2% |
| LMArena Coding | 1173 | 1268 |
| BigCodeBench Complete | 40.6% | 58.2% |
| WeirdML | — | 18% |
| LiveBench Coding | 22.5% | — |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |

## Agentic & Tool Use

- Gemma 2 9B: —
- GPT-4 Turbo: —

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | — | 36.7% |

## Reasoning

- Gemma 2 9B: 15.9 (#309)
- GPT-4 Turbo: 15.3 (#317)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1251 |
| Epoch Capabilities Index | 119.83 | 127.25 |
| SimpleBench | — | 25.1% |
| Chess Puzzles | — | 6% |
| LiveBench Reasoning | 15.2% | — |
| DTBench | — | 61.6% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 9.8% |
| ForecastBench | — | 59.4 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.9 (#318)
- GPT-4 Turbo: 9.0 (#322)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 6.7% |
| LMArena Math | 1183 | 1272 |
| MATH Level 5 | 21% | 46.7% |
| FrontierMath (Tiers 1-3) | — | 0.7% |
| LiveBench Math | 19.8% | — |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#305)
- GPT-4 Turbo: 24.3 (#268)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| GPQA Diamond | 27.5% | 46.6% |
| LMArena Expert | 1147 | 1223 |
| MMLU | 72.1% | 81.3% |
| Confabulations | — | 28.4% |
| BoolQ | 85.7% | — |

## Multimodal

- Gemma 2 9B: —
- GPT-4 Turbo: 30.6 (#110)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |

## Multilingual

- Gemma 2 9B: 36.6 (#238)
- GPT-4 Turbo: 40.5 (#216)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1188 | 1245 |
| LMArena Chinese | 1185 | 1242 |
| LMArena French | 1190 | 1276 |
| LMArena German | 1186 | 1259 |
| LMArena Japanese | 1144 | 1194 |
| LMArena Korean | 1137 | 1187 |
| LMArena Russian | 1200 | 1259 |
| LMArena Spanish | 1200 | 1260 |

## Instruction Following

- Gemma 2 9B: 57.6 (#269)
- GPT-4 Turbo: 65.8 (#216)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1178 | 1249 |
| LiveBench Instruction Following | 52.6% | — |

## Long Context

- Gemma 2 9B: 36.3 (#233)
- GPT-4 Turbo: 38.0 (#206)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | 1197 | 1254 |

## Writing & Preference

- Gemma 2 9B: 32.1 (#281)
- GPT-4 Turbo: 47.7 (#206)

| Benchmark | Gemma 2 9B | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1207 | 1272 |
| LMArena Creative Writing | 1206 | 1269 |
| LMArena Multi-Turn | 1193 | 1267 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than GPT-4 Turbo?

GPT-4 Turbo is the stronger model overall, scoring 30.5 to 25.9 on the Noometry Index.

### Is Gemma 2 9B or GPT-4 Turbo better for coding?

GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 29.4 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and GPT-4 Turbo share?

24 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GPT-4 Turbo has 36.