# Gemma 3 12B vs Mercury 2

> Mercury 2 is the stronger model overall, scoring 39.1 to 32.1 on the Noometry Index. Gemma 3 12B costs 5.0× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and Mercury 2 in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Mercury 2 leads 36.2 to 26.5.
- The biggest single-benchmark swing is SciCode: 17.4% for Gemma 3 12B and 38.7% for Mercury 2.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.25 / $0.75 for Mercury 2.
- Gemma 3 12B accepts more context: 131K tokens versus 128K.
- Gemma 3 12B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3 12B | Mercury 2 |
|---|---|---|
| Provider | Google | Inception |
| Noometry Index | 32.1 | 39.1 |
| Rank | 262 | 175 |
| Context | 131K | 128K |
| Input $/M | $0.05 | $0.25 |
| Output $/M | $0.15 | $0.75 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 12B: 31.7 (#280)
- Mercury 2: 33.5 (#255)

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| SciCode | 17.4% | 38.7% |
| LMArena Coding | 1281 | 1391 |
| LMArena WebDev | — | 1171 |
| WeirdML | — | 43.2% |
| ALE-Bench | — | 785.58 |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- Mercury 2: —

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- Mercury 2: 23.8 (#170)

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| CritPt | 0% | 0.8% |
| LMArena Hard Prompts | 1309 | 1362 |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |

## Math

- Gemma 3 12B: 22.3 (#279)
- Mercury 2: —

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| LMArena Math | 1307 | — |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- Mercury 2: 36.2 (#172)

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | 4.4% | 12.3% |
| LMArena Expert | 1248 | 1358 |
| GPQA Diamond | 39.5% | — |

## Multimodal

- Gemma 3 12B: —
- Mercury 2: —

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- Mercury 2: 46.6 (#157)

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| LMArena Non-English | 1318 | 1331 |
| LMArena Russian | 1335 | 1304 |
| LMArena Chinese | — | 1417 |
| LMArena German | 1370 | — |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- Mercury 2: 70.2 (#165)

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1299 | 1329 |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- Mercury 2: 40.5 (#154)

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| LMArena Longer Query | 1317 | 1330 |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- Mercury 2: 53.8 (#155)

| Benchmark | Gemma 3 12B | Mercury 2 |
|---|---|---|
| LMArena Text | 1334 | 1355 |
| LMArena Creative Writing | 1331 | 1289 |
| LMArena Multi-Turn | 1334 | 1358 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Mercury 2?

Mercury 2 is the stronger model overall, scoring 39.1 to 32.1 on the Noometry Index. Gemma 3 12B costs 5.0× less per token, which makes it the better buy when Mercury 2's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 12B or Mercury 2?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Mercury 2 lists at $0.25 and $0.75.

### Is Gemma 3 12B or Mercury 2 better for coding?

Mercury 2 scores higher on coding benchmarks: 33.5 versus 31.7 in the Noometry coding category.

### Which has the bigger context window?

Gemma 3 12B does, with 131K tokens against 128K.

### How many benchmarks do Gemma 3 12B and Mercury 2 share?

13 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Mercury 2 has 17.