# Gemma 2 27B vs Step 5 Preview

> Step 5 Preview is the stronger model overall, scoring 47.9 to 29.4 on the Noometry Index. Gemma 2 27B costs 2.2× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemma-2-27b-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 5 Preview leads 46.1 to 10.7.
- Gemma 2 27B is cheaper at $0.65 / $0.65 per million input/output tokens, against $1 / $2.70 for Step 5 Preview.
- Step 5 Preview accepts more context: 1.02M tokens versus 8K.
- Gemma 2 27B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| Provider | Google | StepFun |
| Noometry Index | 29.4 | 47.9 |
| Rank | 312 | 58 |
| Context | 8K | 1.02M |
| Input $/M | $0.65 | $1 |
| Output $/M | $0.65 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Gemma 2 27B: 34.1 (#246)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1211 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |

## Reasoning

- Gemma 2 27B: 15.3 (#315)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1465 |
| CritPt | — | 20.9% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |

## Math

- Gemma 2 27B: 10.7 (#311)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1212 | 1470 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| ProofBench | — | 42% |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |

## Knowledge

- Gemma 2 27B: 19.0 (#280)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1172 | 1470 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| MMLU | 75.7% | — |

## Multimodal

- Gemma 2 27B: —
- Step 5 Preview: 41.0 (#41)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |

## Multilingual

- Gemma 2 27B: 38.6 (#226)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1217 | 1432 |
| LMArena Chinese | 1221 | 1519 |
| LMArena Russian | 1234 | 1436 |
| LMArena Spanish | 1228 | 1439 |
| LMArena French | 1247 | — |
| LMArena German | 1209 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1174 | — |

## Instruction Following

- Gemma 2 27B: 60.5 (#249)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1206 | 1444 |
| LiveBench Instruction Following | 58.1% | — |

## Long Context

- Gemma 2 27B: 37.3 (#218)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1231 | 1455 |

## Writing & Preference

- Gemma 2 27B: 44.2 (#225)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Gemma 2 27B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1231 | 1442 |
| LMArena Creative Writing | 1241 | 1410 |
| LMArena Multi-Turn | 1224 | 1447 |
| LiveBench Language | 32.6% | — |

## FAQ

### Is Gemma 2 27B better than Step 5 Preview?

Step 5 Preview is the stronger model overall, scoring 47.9 to 29.4 on the Noometry Index. Gemma 2 27B costs 2.2× less per token, which makes it the better buy when Step 5 Preview's lead doesn't matter for your workload.

### Which is cheaper, Gemma 2 27B or Step 5 Preview?

Gemma 2 27B is cheaper. It lists at $0.65 per million input tokens and $0.65 per million output tokens; Step 5 Preview lists at $1 and $2.70.

### Is Gemma 2 27B or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 8K.

### How many benchmarks do Gemma 2 27B and Step 5 Preview share?

13 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Step 5 Preview has 18.