# Gemma 3 4B vs GPT-5-Codex

> GPT-5-Codex is the stronger model overall, scoring 37.3 to 27.9 on the Noometry Index. Gemma 3 4B costs 69× less per token, which makes it the better buy when GPT-5-Codex's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-4b-vs-gpt-5-codex
- Last updated: 2026-10-10
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Gemma 3 4B scores higher in 0 categories and GPT-5-Codex in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5-Codex leads 30.0 to 12.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 25.2% for Gemma 3 4B and 70.3% for GPT-5-Codex.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex 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-Codex |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 27.9 | 37.3 |
| Rank | 320 | 190 |
| Context | 131K | 400K |
| Input $/M | $0.04 | $1.25 |
| Output $/M | $0.08 | $10 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 4B: 35.3 (#214)
- GPT-5-Codex: 41.9 (#100)

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| WeirdML | — | 54.5% |
| LMArena Coding | 1230 | — |

## Agentic & Tool Use

- Gemma 3 4B: 20.7 (#134)
- GPT-5-Codex: 30.8 (#66)

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
| Berkeley Function Calling Leaderboard | 19.6% | — |

## Reasoning

- Gemma 3 4B: 12.7 (#330)
- GPT-5-Codex: 30.0 (#80)

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | 70.3% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1253 | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |

## Math

- Gemma 3 4B: 15.8 (#286)
- GPT-5-Codex: —

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| LMArena Math | 1239 | — |

## Knowledge

- Gemma 3 4B: 11.8 (#294)
- GPT-5-Codex: —

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |

## Multilingual

- Gemma 3 4B: 42.7 (#189)
- GPT-5-Codex: —

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |

## Instruction Following

- Gemma 3 4B: 65.4 (#219)
- GPT-5-Codex: —

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1239 | — |

## Long Context

- Gemma 3 4B: 38.6 (#189)
- GPT-5-Codex: —

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 1274 | — |

## Writing & Preference

- Gemma 3 4B: 42.2 (#234)
- GPT-5-Codex: —

| Benchmark | Gemma 3 4B | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1270 | — |
| EQ-Bench Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1255 | — |

## FAQ

### Is Gemma 3 4B better than GPT-5-Codex?

GPT-5-Codex is the stronger model overall, scoring 37.3 to 27.9 on the Noometry Index. Gemma 3 4B costs 69× less per token, which makes it the better buy when GPT-5-Codex's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 4B or GPT-5-Codex?

Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

### Is Gemma 3 4B or GPT-5-Codex better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 35.3 in the Noometry coding category.

### Which has the bigger context window?

GPT-5-Codex does, with 400K tokens against 131K.

### How many benchmarks do Gemma 3 4B and GPT-5-Codex share?

1 benchmark has published results for both models. Gemma 3 4B has 22 scored results on Noometry and GPT-5-Codex has 3.