# Gemma 2B vs GPT-5.4 nano

> GPT-5.4 nano is the stronger model overall, scoring 41.9 to 29.1 on the Noometry Index.

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

## Summary

- They share 12 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and GPT-5.4 nano in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.4 nano leads 55.9 to 24.1.
- Gemma 2B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 29.1 | 41.9 |
| Rank | 305 | 111 |
| Context | — | 400K |
| Input $/M | — | $0.20 |
| Output $/M | — | $1.25 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2B: 28.9 (#300)
- GPT-5.4 nano: 43.1 (#82)

| Benchmark | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| LMArena Coding | 1010 | 1404 |
| SciCode | — | 46.9% |
| WeirdML | — | 49.2% |
| ALE-Bench | — | 1,005 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |

## Reasoning

- Gemma 2B: 17.9 (#275)
- GPT-5.4 nano: 23.8 (#159)

| Benchmark | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| LMArena Hard Prompts | 989 | 1380 |
| Epoch Capabilities Index | 93.57 | 145.78 |
| ARC-AGI-2 | — | 5.7% |
| Kagi LLM Benchmark | — | 39.7% |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 36.9% |
| BIG-Bench Hard | 35.2% | — |
| ForecastBench | — | 57.3 |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |

## Math

- Gemma 2B: 27.6 (#237)
- GPT-5.4 nano: 40.7 (#76)

| Benchmark | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| LMArena Math | 1009 | 1406 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 87.8% |
| ProofBench | — | 5% |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
| GSM8K | 17.7% | — |

## Knowledge

- Gemma 2B: —
- GPT-5.4 nano: 41.8 (#94)

| Benchmark | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | — | 78.5% |
| SimpleQA Verified | — | 11.7% |
| Vectara Hallucination Rate | — | 3.1% |
| LMArena Expert | — | 1397 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |

## Multimodal

- Gemma 2B: —
- GPT-5.4 nano: 36.0 (#73)

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

## Multilingual

- Gemma 2B: 23.1 (#289)
- GPT-5.4 nano: 48.8 (#136)

| Benchmark | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 958 | 1359 |
| LMArena Chinese | 986 | 1391 |
| LMArena Russian | 937 | 1363 |
| LMArena French | — | 1396 |
| LMArena German | — | 1368 |
| LMArena Japanese | — | 1342 |
| LMArena Korean | — | 1321 |
| LMArena Spanish | — | 1368 |

## Instruction Following

- Gemma 2B: 48.8 (#297)
- GPT-5.4 nano: 72.1 (#139)

| Benchmark | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 971 | 1362 |

## Long Context

- Gemma 2B: 29.9 (#286)
- GPT-5.4 nano: 41.6 (#131)

| Benchmark | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 981 | 1365 |

## Writing & Preference

- Gemma 2B: 24.1 (#303)
- GPT-5.4 nano: 55.9 (#137)

| Benchmark | Gemma 2B | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1002 | 1372 |
| LMArena Creative Writing | 986 | 1313 |
| LMArena Multi-Turn | 945 | 1382 |

## FAQ

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

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 29.1 on the Noometry Index.

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

GPT-5.4 nano scores higher on coding benchmarks: 43.1 versus 28.9 in the Noometry coding category.

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

12 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and GPT-5.4 nano has 40.