# Gemma 7B vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 29.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-7b-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3.5 Flash leads 59.0 to 27.2.

## Snapshot

| | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| Provider | Google | StepFun |
| Noometry Index | 29.5 | 41.7 |
| Rank | 295 | 116 |
| Context | — | 256K |
| Input $/M | — | $0.10 |
| Output $/M | — | $0.30 |
| Weights | Open | Open |

## Coding

- Gemma 7B: 29.9 (#290)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1048 | 1436 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |

## Reasoning

- Gemma 7B: 19.0 (#247)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.74 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |

## Math

- Gemma 7B: 28.7 (#225)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1066 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| GSM8K | 46.4% | — |

## Knowledge

- Gemma 7B: 26.8 (#248)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1002 | 1422 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |

## Multilingual

- Gemma 7B: 25.3 (#282)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 999 | 1386 |
| LMArena Chinese | 1035 | 1448 |
| LMArena French | 1024 | 1421 |
| LMArena Russian | 993 | 1385 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |
| LMArena Spanish | — | 1419 |

## Instruction Following

- Gemma 7B: 51.7 (#290)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1017 | 1385 |

## Long Context

- Gemma 7B: 31.1 (#277)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1022 | 1402 |

## Writing & Preference

- Gemma 7B: 27.2 (#297)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Gemma 7B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1056 | 1403 |
| LMArena Creative Writing | 1024 | 1357 |
| LMArena Multi-Turn | 963 | 1405 |

## FAQ

### Is Gemma 7B better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 29.5 on the Noometry Index.

### Is Gemma 7B or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 29.9 in the Noometry coding category.

### How many benchmarks do Gemma 7B and Step 3.5 Flash share?

13 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Step 3.5 Flash has 19.