# Gemma 3 4B vs GPT-5.4 mini

> GPT-5.4 mini is the stronger model overall, scoring 45.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 34× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-gpt-5-4-mini
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemma 3 4B scores higher in 0 categories and GPT-5.4 mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 11.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 7.5% for Gemma 3 4B and 88.9% for GPT-5.4 mini.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 131K.
- Gemma 3 4B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 28.1 | 45.0 |
| Rank | 326 | 76 |
| Context | 131K | 400K |
| Input $/M | $0.04 | $0.75 |
| Output $/M | $0.08 | $4.50 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 4B: 35.9 (#215)
- GPT-5.4 mini: 45.2 (#72)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| LMArena Coding | 1230 | 1438 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| WeirdML | — | 60.3% |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- Gemma 3 4B: 20.9 (#142)
- GPT-5.4 mini: 29.9 (#81)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
| DeepResearch Bench | — | 36.3% |

## Reasoning

- Gemma 3 4B: 13.2 (#335)
- GPT-5.4 mini: 30.4 (#85)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 37.9% |
| Chess Puzzles | 0% | 24% |
| LMArena Hard Prompts | 1253 | 1424 |
| DTBench | 50.9% | 80% |
| LMCA | 2.8% | 40.8% |
| Epoch Capabilities Index | 116.02 | 148.84 |
| ARC-AGI-2 | — | 18.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| CritPt | — | 10% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| ForecastBench | — | 57 |

## Math

- Gemma 3 4B: 16.8 (#292)
- GPT-5.4 mini: 45.5 (#75)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | 88.9% |
| LMArena Math | 1239 | 1419 |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- Gemma 3 4B: 11.8 (#299)
- GPT-5.4 mini: 51.5 (#67)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 23.2% | 86.9% |
| Vectara Hallucination Rate | 6.4% | 5.5% |
| LMArena Expert | 1223 | 1435 |
| SimpleQA Verified | — | 29.4% |

## Multimodal

- Gemma 3 4B: —
- GPT-5.4 mini: 39.7 (#56)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |

## Multilingual

- Gemma 3 4B: 42.5 (#194)
- GPT-5.4 mini: 51.9 (#96)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1273 | 1405 |
| LMArena German | 1281 | 1409 |
| LMArena Russian | 1294 | 1417 |
| LMArena Chinese | — | 1446 |
| LMArena French | — | 1440 |
| LMArena Japanese | — | 1374 |
| LMArena Korean | — | 1368 |
| LMArena Spanish | — | 1405 |

## Instruction Following

- Gemma 3 4B: 65.2 (#225)
- GPT-5.4 mini: 74.1 (#102)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1239 | 1405 |

## Long Context

- Gemma 3 4B: 38.7 (#194)
- GPT-5.4 mini: 43.0 (#112)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1273 | 1407 |

## Writing & Preference

- Gemma 3 4B: 42.0 (#239)
- GPT-5.4 mini: 64.0 (#58)

| Benchmark | Gemma 3 4B | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1291 | 1412 |
| LMArena Creative Writing | 1271 | 1370 |
| EQ-Bench Creative Writing | 1068 | 1665 |
| LMArena Multi-Turn | 1255 | 1429 |

## FAQ

### Is Gemma 3 4B better than GPT-5.4 mini?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 28.1 on the Noometry Index. Gemma 3 4B costs 34× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 4B or GPT-5.4 mini?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

### Is Gemma 3 4B or GPT-5.4 mini better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 35.9 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 131K.

### How many benchmarks do Gemma 3 4B and GPT-5.4 mini share?

21 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and GPT-5.4 mini has 46.