# Gemma 2 9B vs GPT-4.5

> GPT-4.5 is the stronger model overall, scoring 36.9 to 25.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Gemma 2 9B scores higher in 1 category and GPT-4.5 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4.5 leads 57.1 to 32.3.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 78.6% for GPT-4.5.
- Gemma 2 9B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 25.7 | 36.9 |
| Rank | 334 | 200 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 9B: 29.0 (#299)
- GPT-4.5: 41.8 (#102)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| LiveBench Coding | 22.5% | 75.2% |
| LMArena Coding | 1174 | 1397 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
| BigCodeBench Instruct | 34.7% | — |
| BigCodeBench Complete | 40.6% | — |

## Agentic & Tool Use

- Gemma 2 9B: —
- GPT-4.5: 27.6 (#92)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |

## Reasoning

- Gemma 2 9B: 15.3 (#306)
- GPT-4.5: 14.1 (#320)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| LiveBench Reasoning | 15.2% | 71.1% |
| LMArena Hard Prompts | 1172 | 1404 |
| LiveBench Data Analysis | 36.4% | 64.3% |
| Epoch Capabilities Index | 119.78 | 136.74 |
| LiveBench | 28.7% | 69% |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| ARC-AGI-1 | — | 10.3% |
| EnigmaEval | — | 3.2% |
| ForecastBench | — | 61.7 |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.3 (#312)
- GPT-4.5: 31.0 (#200)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 37.8% |
| LiveBench Math | 19.8% | 69.3% |
| LMArena Math | 1183 | 1412 |
| MATH Level 5 | 21% | 78.6% |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#300)
- GPT-4.5: 32.4 (#205)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| GPQA Diamond | 27.5% | 68.7% |
| LMArena Expert | 1147 | 1394 |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multimodal

- Gemma 2 9B: —
- GPT-4.5: 37.0 (#68)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| LMArena Vision | — | 1195 |
| VPCT | — | 45% |

## Multilingual

- Gemma 2 9B: 36.8 (#233)
- GPT-4.5: 52.7 (#78)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1188 | 1413 |
| LMArena Chinese | 1185 | 1421 |
| LMArena French | 1189 | 1417 |
| LMArena German | 1186 | 1457 |
| LMArena Japanese | 1144 | 1416 |
| LMArena Korean | 1137 | 1392 |
| LMArena Russian | 1200 | 1419 |
| LMArena Spanish | 1200 | — |

## Instruction Following

- Gemma 2 9B: 57.8 (#264)
- GPT-4.5: 72.8 (#129)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| LiveBench Instruction Following | 52.6% | 72.3% |
| LMArena Instruction Following | 1178 | 1404 |

## Long Context

- Gemma 2 9B: 36.3 (#228)
- GPT-4.5: 40.4 (#150)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1197 | 1406 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- Gemma 2 9B: 32.3 (#276)
- GPT-4.5: 57.1 (#129)

| Benchmark | Gemma 2 9B | GPT-4.5 |
|---|---|---|
| LMArena Text | 1207 | 1417 |
| LMArena Creative Writing | 1206 | 1394 |
| EQ-Bench Creative Writing | 841 | 1258 |
| LMArena Multi-Turn | 1193 | 1444 |
| LiveBench Language | 25.5% | 61.5% |
| Short-Story Creative Writing | — | 75.6% |

## FAQ

### Is Gemma 2 9B better than GPT-4.5?

GPT-4.5 is the stronger model overall, scoring 36.9 to 25.7 on the Noometry Index.

### Is Gemma 2 9B or GPT-4.5 better for coding?

GPT-4.5 scores higher on coding benchmarks: 41.8 versus 29.0 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and GPT-4.5 share?

28 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GPT-4.5 has 42.