# DBRX vs Gemma 3 27B

> Gemma 3 27B is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/dbrx-vs-gemma-3-27b
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. DBRX scores higher in 3 categories and Gemma 3 27B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 33.6.
- The biggest single-benchmark swing is MATH Level 5: 11.7% for DBRX and 74% for Gemma 3 27B.

## Snapshot

| | DBRX | Gemma 3 27B |
|---|---|---|
| Provider | Databricks | Google |
| Noometry Index | 29.4 | 30.8 |
| Rank | 311 | 284 |
| Context | — | 131K |
| Input $/M | — | $0.08 |
| Output $/M | — | $0.16 |
| Weights | Open | Open |

## Coding

- DBRX: 32.9 (#266)
- Gemma 3 27B: 22.5 (#334)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| LMArena Coding | 1132 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
| LiveBench Coding | — | 39.9% |
| HumanEval+ | 70.1% | — |
| MBPP+ | 55.8% | — |

## Agentic & Tool Use

- DBRX: —
- Gemma 3 27B: 25.1 (#110)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |

## Reasoning

- DBRX: 21.4 (#222)
- Gemma 3 27B: 16.7 (#301)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1340 |
| Kagi LLM Benchmark | — | 40.4% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 43.8% |
| DTBench | — | 52.5% |
| LiveBench Data Analysis | — | 51.5% |
| LMCA | — | 12.3% |
| Epoch Capabilities Index | — | 130.04 |
| LiveBench | — | 50% |

## Math

- DBRX: 24.3 (#269)
- Gemma 3 27B: 25.9 (#265)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| LMArena Math | 1145 | 1312 |
| MATH Level 5 | 11.7% | 74% |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| LiveBench Math | — | 55.4% |

## Knowledge

- DBRX: 14.9 (#294)
- Gemma 3 27B: 25.5 (#261)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | 32.9% | 47.7% |
| LMArena Expert | 1076 | 1304 |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |

## Multimodal

- DBRX: —
- Gemma 3 27B: 32.6 (#100)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1164 |
| GeoBench | — | 52% |

## Multilingual

- DBRX: 29.3 (#268)
- Gemma 3 27B: 46.9 (#155)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1071 | 1334 |
| LMArena Chinese | 1068 | 1346 |
| LMArena French | 1096 | 1368 |
| LMArena German | 1057 | 1362 |
| LMArena Japanese | 990 | 1287 |
| LMArena Korean | 993 | 1308 |
| LMArena Russian | 1078 | 1349 |
| LMArena Spanish | 1064 | 1349 |

## Instruction Following

- DBRX: 57.5 (#270)
- Gemma 3 27B: 70.6 (#160)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1112 | 1321 |
| LiveBench Instruction Following | — | 74.9% |

## Long Context

- DBRX: 33.7 (#258)
- Gemma 3 27B: 27.6 (#293)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1112 | 1333 |
| Fiction.LiveBench | — | 33.3% |

## Writing & Preference

- DBRX: 33.6 (#275)
- Gemma 3 27B: 52.5 (#168)

| Benchmark | DBRX | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1119 | 1358 |
| LMArena Creative Writing | 1104 | 1346 |
| LMArena Multi-Turn | 1111 | 1345 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| LiveBench Language | — | 34.6% |

## FAQ

### Is DBRX better than Gemma 3 27B?

Gemma 3 27B is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.

### Is DBRX or Gemma 3 27B better for coding?

DBRX scores higher on coding benchmarks: 32.9 versus 22.5 in the Noometry coding category.

### How many benchmarks do DBRX and Gemma 3 27B share?

19 benchmarks have published results for both models. DBRX has 21 scored results on Noometry and Gemma 3 27B has 43.