# Gemma 2 9B vs GPT-5.4 nano

> GPT-5.4 nano is the stronger model overall, scoring 41.9 to 25.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2-9b-vs-gpt-5-4-nano
- Last updated: 2026-10-12
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and GPT-5.4 nano in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 nano leads 41.9 to 9.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.6% for Gemma 2 9B and 87.8% for GPT-5.4 nano.
- Gemma 2 9B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 25.9 | 41.9 |
| Rank | 341 | 125 |
| Context | — | 400K |
| Input $/M | — | $0.20 |
| Output $/M | — | $1.25 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 9B: 29.4 (#304)
- GPT-5.4 nano: 43.6 (#84)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| LMArena Coding | 1173 | 1405 |
| SciCode | — | 46.9% |
| WeirdML | — | 49.2% |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| ALE-Bench | — | 1,005 |

## Reasoning

- Gemma 2 9B: 15.9 (#309)
- GPT-5.4 nano: 23.7 (#173)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1381 |
| Epoch Capabilities Index | 119.83 | 145.81 |
| ARC-AGI-2 | — | 5.7% |
| Kagi LLM Benchmark | — | 39.7% |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| LiveBench Reasoning | 15.2% | — |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LiveBench Data Analysis | 36.4% | — |
| LMCA | — | 36.9% |
| ForecastBench | — | 57.3 |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |

## Math

- Gemma 2 9B: 9.9 (#318)
- GPT-5.4 nano: 40.9 (#88)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 87.8% |
| LMArena Math | 1183 | 1406 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| ProofBench | — | 5% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
| GSM8K | 84.9% | — |

## Knowledge

- Gemma 2 9B: 9.7 (#305)
- GPT-5.4 nano: 41.9 (#103)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 27.5% | 78.5% |
| LMArena Expert | 1147 | 1396 |
| SimpleQA Verified | — | 11.7% |
| Vectara Hallucination Rate | — | 3.1% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |

## Multimodal

- Gemma 2 9B: —
- GPT-5.4 nano: 36.7 (#78)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | — | 1196 |

## Multilingual

- Gemma 2 9B: 36.6 (#238)
- GPT-5.4 nano: 48.6 (#140)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1188 | 1359 |
| LMArena Chinese | 1185 | 1392 |
| LMArena French | 1190 | 1396 |
| LMArena German | 1186 | 1367 |
| LMArena Japanese | 1144 | 1343 |
| LMArena Korean | 1137 | 1320 |
| LMArena Russian | 1200 | 1363 |
| LMArena Spanish | 1200 | 1371 |

## Instruction Following

- Gemma 2 9B: 57.6 (#269)
- GPT-5.4 nano: 71.9 (#144)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1178 | 1362 |
| LiveBench Instruction Following | 52.6% | — |

## Long Context

- Gemma 2 9B: 36.3 (#233)
- GPT-5.4 nano: 41.6 (#137)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1197 | 1366 |

## Writing & Preference

- Gemma 2 9B: 32.1 (#281)
- GPT-5.4 nano: 55.7 (#142)

| Benchmark | Gemma 2 9B | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1207 | 1372 |
| LMArena Creative Writing | 1206 | 1314 |
| LMArena Multi-Turn | 1193 | 1382 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |

## FAQ

### Is Gemma 2 9B better than GPT-5.4 nano?

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 25.9 on the Noometry Index.

### Is Gemma 2 9B or GPT-5.4 nano better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 29.4 in the Noometry coding category.

### How many benchmarks do Gemma 2 9B and GPT-5.4 nano share?

20 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and GPT-5.4 nano has 40.