# Gemma 3 12B vs Yi-34B

> Gemma 3 12B is the stronger model overall, scoring 32.1 to 27.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-12b-vs-yi-34b
- Last updated: 2026-10-10
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. Gemma 3 12B scores higher in 6 categories and Yi-34B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Gemma 3 12B leads 26.5 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 39.5% for Gemma 3 12B and 14.7% for Yi-34B.

## Snapshot

| | Gemma 3 12B | Yi-34B |
|---|---|---|
| Provider | Google | 01.AI |
| Noometry Index | 32.1 | 27.8 |
| Rank | 262 | 329 |
| Context | 131K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.15 | — |
| Weights | Open | Open |

## Coding

- Gemma 3 12B: 31.7 (#280)
- Yi-34B: 32.3 (#274)

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| LMArena Coding | 1281 | 1112 |
| SciCode | 17.4% | — |

## Agentic & Tool Use

- Gemma 3 12B: 25.5 (#108)
- Yi-34B: —

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |

## Reasoning

- Gemma 3 12B: 15.7 (#313)
- Yi-34B: 21.2 (#226)

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1104 |
| Epoch Capabilities Index | 123.5 | 117.39 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| BIG-Bench Hard | — | 71.7% |

## Math

- Gemma 3 12B: 22.3 (#279)
- Yi-34B: 21.6 (#282)

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| LMArena Math | 1307 | 1114 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- Gemma 3 12B: 26.5 (#257)
- Yi-34B: 7.5 (#309)

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| GPQA Diamond | 39.5% | 14.7% |
| LMArena Expert | 1248 | 1061 |
| Vectara Hallucination Rate | 4.4% | — |
| MMLU | — | 76.3% |

## Multimodal

- Gemma 3 12B: —
- Yi-34B: —

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| MindCube | 46.7% | — |

## Multilingual

- Gemma 3 12B: 45.7 (#165)
- Yi-34B: 29.7 (#264)

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| LMArena Non-English | 1318 | 1079 |
| LMArena German | 1370 | 1042 |
| LMArena Russian | 1335 | 1050 |
| LMArena Chinese | — | 1176 |
| LMArena French | — | 1081 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Spanish | — | 1070 |

## Instruction Following

- Gemma 3 12B: 68.6 (#186)
- Yi-34B: 56.2 (#274)

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1091 |

## Long Context

- Gemma 3 12B: 40.0 (#162)
- Yi-34B: 33.2 (#264)

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1317 | 1094 |

## Writing & Preference

- Gemma 3 12B: 47.5 (#209)
- Yi-34B: 34.1 (#273)

| Benchmark | Gemma 3 12B | Yi-34B |
|---|---|---|
| LMArena Text | 1334 | 1129 |
| LMArena Creative Writing | 1331 | 1108 |
| LMArena Multi-Turn | 1334 | 1113 |
| EQ-Bench Creative Writing | 1126 | — |

## FAQ

### Is Gemma 3 12B better than Yi-34B?

Gemma 3 12B is the stronger model overall, scoring 32.1 to 27.8 on the Noometry Index.

### Is Gemma 3 12B or Yi-34B better for coding?

They score almost the same on coding (31.7 vs 32.3); test both on your own repository before choosing.

### How many benchmarks do Gemma 3 12B and Yi-34B share?

14 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Yi-34B has 23.