# Gemma 2B vs GPT-5-Codex

> GPT-5-Codex is the stronger model overall, scoring 37.3 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-2b-vs-gpt-5-codex
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5-Codex leads 41.9 to 28.9.
- Gemma 2B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2B | GPT-5-Codex |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 29.1 | 37.3 |
| Rank | 305 | 190 |
| Context | — | 400K |
| Input $/M | — | $1.25 |
| Output $/M | — | $10 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2B: 28.9 (#300)
- GPT-5-Codex: 41.9 (#100)

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| WeirdML | — | 54.5% |
| LMArena Coding | 1010 | — |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |

## Agentic & Tool Use

- Gemma 2B: —
- GPT-5-Codex: 30.8 (#66)

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |

## Reasoning

- Gemma 2B: 17.9 (#275)
- GPT-5-Codex: 30.0 (#80)

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | — | 70.3% |
| LMArena Hard Prompts | 989 | — |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 93.57 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |

## Math

- Gemma 2B: 27.6 (#237)
- GPT-5-Codex: —

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| LMArena Math | 1009 | — |
| GSM8K | 17.7% | — |

## Knowledge

- Gemma 2B: —
- GPT-5-Codex: —

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |

## Multilingual

- Gemma 2B: 23.1 (#289)
- GPT-5-Codex: —

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 958 | — |
| LMArena Chinese | 986 | — |
| LMArena Russian | 937 | — |

## Instruction Following

- Gemma 2B: 48.8 (#297)
- GPT-5-Codex: —

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 971 | — |

## Long Context

- Gemma 2B: 29.9 (#286)
- GPT-5-Codex: —

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 981 | — |

## Writing & Preference

- Gemma 2B: 24.1 (#303)
- GPT-5-Codex: —

| Benchmark | Gemma 2B | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1002 | — |
| LMArena Creative Writing | 986 | — |
| LMArena Multi-Turn | 945 | — |

## FAQ

### Is Gemma 2B better than GPT-5-Codex?

GPT-5-Codex is the stronger model overall, scoring 37.3 to 29.1 on the Noometry Index.

### Is Gemma 2B or GPT-5-Codex better for coding?

GPT-5-Codex scores higher on coding benchmarks: 41.9 versus 28.9 in the Noometry coding category.

### How many benchmarks do Gemma 2B and GPT-5-Codex share?

0 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and GPT-5-Codex has 3.