# Gemma 3 12B vs Trinity Large Thinking

> Trinity Large Thinking is the stronger model overall, scoring 38.1 to 31.8 on the Noometry Index. Gemma 3 12B costs 5.2× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-trinity-large-thinking
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemma 3 12B scores higher in 0 categories and Trinity Large Thinking in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Trinity Large Thinking leads 34.9 to 21.0.
- The biggest single-benchmark swing is SciCode: 17.4% for Gemma 3 12B and 36.1% for Trinity Large Thinking.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- Trinity Large Thinking accepts more context: 262K tokens versus 131K.

## Snapshot

| | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| Provider | Google | Arcee AI |
| Noometry Index | 31.8 | 38.1 |
| Rank | 255 | 180 |
| Context | 131K | 262K |
| Input $/M | $0.05 | $0.25 |
| Output $/M | $0.15 | $0.80 |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.2 (#276)
- Trinity Large Thinking: 33.8 (#238)

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| SciCode | 17.4% | 36.1% |
| LMArena Coding | 1281 | 1381 |
| LMArena WebDev | — | 1238 |

## Agentic & Tool Use

- Gemma 3 12B: 25.3 (#101)
- Trinity Large Thinking: —

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.2 (#307)
- Trinity Large Thinking: 16.3 (#298)

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| CritPt | 0% | 0.9% |
| LMArena Hard Prompts | 1309 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 41.6% |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Surface Evolver Bench | — | 15.6% |
| Epoch Capabilities Index | 123.49 | — |

## Math

- Gemma 3 12B: 21.0 (#273)
- Trinity Large Thinking: 34.9 (#149)

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1307 | 1366 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |

## Knowledge

- Gemma 3 12B: 26.5 (#250)
- Trinity Large Thinking: 40.3 (#107)

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| Vectara Hallucination Rate | 4.4% | 6.9% |
| LMArena Expert | 1248 | 1359 |
| GPQA Diamond | 39.5% | — |

## Multimodal

- Gemma 3 12B: —
- Trinity Large Thinking: —

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.9 (#160)
- Trinity Large Thinking: 46.4 (#155)

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1318 | 1325 |
| LMArena German | 1370 | 1356 |
| LMArena Russian | 1335 | 1338 |
| LMArena Chinese | — | 1372 |
| LMArena French | — | 1374 |
| LMArena Japanese | — | 1312 |
| LMArena Korean | — | 1304 |
| LMArena Spanish | — | 1356 |

## Instruction Following

- Gemma 3 12B: 68.8 (#179)
- Trinity Large Thinking: 70.7 (#157)

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1299 | 1334 |

## Long Context

- Gemma 3 12B: 40.0 (#157)
- Trinity Large Thinking: 41.2 (#139)

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1317 | 1355 |

## Writing & Preference

- Gemma 3 12B: 47.7 (#205)
- Trinity Large Thinking: 54.0 (#152)

| Benchmark | Gemma 3 12B | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1334 | 1340 |
| LMArena Creative Writing | 1331 | 1321 |
| LMArena Multi-Turn | 1334 | 1342 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Trinity Large Thinking?

Trinity Large Thinking is the stronger model overall, scoring 38.1 to 31.8 on the Noometry Index. Gemma 3 12B costs 5.2× less per token, which makes it the better buy when Trinity Large Thinking's lead doesn't matter for your workload.

### Which is cheaper, Gemma 3 12B or Trinity Large Thinking?

Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.

### Is Gemma 3 12B or Trinity Large Thinking better for coding?

Trinity Large Thinking scores higher on coding benchmarks: 33.8 versus 31.2 in the Noometry coding category.

### Which has the bigger context window?

Trinity Large Thinking does, with 262K tokens against 131K.

### How many benchmarks do Gemma 3 12B and Trinity Large Thinking share?

15 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Trinity Large Thinking has 24.