# Gemma 3 12B vs GPT-5.1-Codex

> GPT-5.1-Codex is the stronger model overall, scoring 38.2 to 31.8 on the Noometry Index. Gemma 3 12B costs 46× less per token, which makes it the better buy when GPT-5.1-Codex's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-gpt-5-1-codex
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in agentic & tool use, where GPT-5.1-Codex leads 37.8 to 25.3.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $1.25 / $10 for GPT-5.1-Codex.
- GPT-5.1-Codex accepts more context: 400K tokens versus 131K.
- Gemma 3 12B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 31.8 | 38.2 |
| Rank | 255 | 178 |
| Context | 131K | 400K |
| Input $/M | $0.05 | $1.25 |
| Output $/M | $0.15 | $10 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 12B: 31.2 (#276)
- GPT-5.1-Codex: 41.7 (#107)

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| SWE-bench Verified (bash only) | — | 66% |
| LMArena WebDev | — | 1337 |
| SciCode | 17.4% | — |
| LMArena Coding | 1281 | — |
| ALE-Bench | — | 1,245 |

## Agentic & Tool Use

- Gemma 3 12B: 25.3 (#101)
- GPT-5.1-Codex: 37.8 (#32)

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| Terminal-Bench | — | 60.4% |
| Berkeley Function Calling Leaderboard | 30.4% | — |
| METR Time Horizons | — | 70.8% |

## Reasoning

- Gemma 3 12B: 15.2 (#307)
- GPT-5.1-Codex: —

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1309 | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |

## Math

- Gemma 3 12B: 21.0 (#273)
- GPT-5.1-Codex: 29.3 (#218)

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| ProofBench | — | 9% |
| LMArena Math | 1307 | — |

## Knowledge

- Gemma 3 12B: 26.5 (#250)
- GPT-5.1-Codex: —

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |

## Multimodal

- Gemma 3 12B: —
- GPT-5.1-Codex: —

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.9 (#160)
- GPT-5.1-Codex: —

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| LMArena Non-English | 1318 | — |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |

## Instruction Following

- Gemma 3 12B: 68.8 (#179)
- GPT-5.1-Codex: —

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| LMArena Instruction Following | 1299 | — |

## Long Context

- Gemma 3 12B: 40.0 (#157)
- GPT-5.1-Codex: —

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| LMArena Longer Query | 1317 | — |

## Writing & Preference

- Gemma 3 12B: 47.7 (#205)
- GPT-5.1-Codex: —

| Benchmark | Gemma 3 12B | GPT-5.1-Codex |
|---|---|---|
| LMArena Text | 1334 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1126 | — |
| LMArena Multi-Turn | 1334 | — |

## FAQ

### Is Gemma 3 12B better than GPT-5.1-Codex?

GPT-5.1-Codex is the stronger model overall, scoring 38.2 to 31.8 on the Noometry Index. Gemma 3 12B costs 46× less per token, which makes it the better buy when GPT-5.1-Codex's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 12B or GPT-5.1-Codex?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; GPT-5.1-Codex lists at $1.25 and $10.

### Is Gemma 3 12B or GPT-5.1-Codex better for coding?

GPT-5.1-Codex scores higher on coding benchmarks: 41.7 versus 31.2 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.1-Codex does, with 400K tokens against 131K.

### How many benchmarks do Gemma 3 12B and GPT-5.1-Codex share?

0 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and GPT-5.1-Codex has 6.