# Gemma 3 12B vs gpt-oss-20b

> Gemma 3 12B and gpt-oss-20b score almost the same on the Noometry Index (32.1 vs 32.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-gpt-oss-20b
- Last updated: 2026-10-12
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and gpt-oss-20b in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where gpt-oss-20b leads 39.4 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.7% for Gemma 3 12B and 65.3% for gpt-oss-20b.
- gpt-oss-20b is cheaper at $0.018 / $0.09 per million input/output tokens, against $0.05 / $0.15 for Gemma 3 12B.

## Snapshot

| | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 32.1 | 32.5 |
| Rank | 262 | 255 |
| Context | 131K | 131K |
| Input $/M | $0.05 | $0.018 |
| Output $/M | $0.15 | $0.09 |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.7 (#280)
- gpt-oss-20b: 37.6 (#192)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| SciCode | 17.4% | 34.4% |
| LMArena Coding | 1281 | 1306 |
| WeirdML | — | 40.9% |
| ALE-Bench | — | 566.05 |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- gpt-oss-20b: 9.3 (#154)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| Terminal-Bench | — | 3.4% |
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- gpt-oss-20b: 19.3 (#261)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| CritPt | 0% | 1.4% |
| Chess Puzzles | 0% | 4% |
| LMArena Hard Prompts | 1309 | 1274 |
| DTBench | 48.8% | 68% |
| LMCA | 4.5% | 14.5% |
| Epoch Capabilities Index | 123.5 | 137.82 |
| Kagi LLM Benchmark | — | 53.2% |

## Math

- Gemma 3 12B: 22.3 (#279)
- gpt-oss-20b: 39.4 (#103)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 65.3% |
| LMArena Math | 1307 | 1317 |
| Omni-MATH | — | 56.5% |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- gpt-oss-20b: 34.6 (#195)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| GPQA Diamond | 39.5% | 60.8% |
| LMArena Expert | 1248 | 1258 |
| MMLU-Pro | — | 74% |
| Vectara Hallucination Rate | 4.4% | — |
| GPQA (HELM) | — | 59.4% |

## Multimodal

- Gemma 3 12B: —
- gpt-oss-20b: —

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- gpt-oss-20b: 42.2 (#197)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| LMArena Non-English | 1318 | 1268 |
| LMArena German | 1370 | 1255 |
| LMArena Russian | 1335 | 1278 |
| LMArena Chinese | — | 1314 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1236 |
| LMArena Spanish | — | 1267 |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- gpt-oss-20b: 61.8 (#240)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| LMArena Instruction Following | 1299 | 1236 |
| IFEval | — | 73.2% |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- gpt-oss-20b: 37.9 (#209)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| LMArena Longer Query | 1317 | 1250 |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- gpt-oss-20b: 35.5 (#265)

| Benchmark | Gemma 3 12B | gpt-oss-20b |
|---|---|---|
| LMArena Text | 1334 | 1287 |
| LMArena Creative Writing | 1331 | 1201 |
| EQ-Bench Creative Writing | 1126 | 666 |
| LMArena Multi-Turn | 1334 | 1268 |
| WildBench | — | 73.7% |

## FAQ

### Is Gemma 3 12B better than gpt-oss-20b?

Gemma 3 12B and gpt-oss-20b score almost the same on the Noometry Index (32.1 vs 32.5), so choose on price, context window or the category you care about most.

### Which is cheaper, Gemma 3 12B or gpt-oss-20b?

gpt-oss-20b is cheaper. It lists at $0.018 per million input tokens and $0.09 per million output tokens; Gemma 3 12B lists at $0.05 and $0.15.

### Is Gemma 3 12B or gpt-oss-20b better for coding?

gpt-oss-20b scores higher on coding benchmarks: 37.6 versus 31.7 in the Noometry coding category.

### Which has the bigger context window?

Both accept 131K tokens.

### How many benchmarks do Gemma 3 12B and gpt-oss-20b share?

21 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and gpt-oss-20b has 34.