# Gemma 1.1 7b IT vs Step 3

> Step 3 is the stronger model overall, scoring 40.5 to 31.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-1-1-7b-it-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Gemma 1.1 7b IT scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 30.4.

## Snapshot

| | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| Provider | Google | StepFun |
| Noometry Index | 31.3 | 40.5 |
| Rank | 277 | 149 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Gemma 1.1 7b IT: 31.5 (#284)
- Step 3: 40.1 (#147)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Coding | 1084 | 1367 |
| HumanEval+ | 35.4% | — |
| MBPP+ | 45% | — |

## Reasoning

- Gemma 1.1 7b IT: 20.5 (#238)
- Step 3: 28.4 (#105)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1071 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |

## Math

- Gemma 1.1 7b IT: 32.0 (#220)
- Step 3: 37.6 (#148)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Math | 1107 | 1366 |

## Knowledge

- Gemma 1.1 7b IT: 28.3 (#247)
- Step 3: 36.8 (#164)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Expert | 1039 | 1333 |

## Multimodal

- Gemma 1.1 7b IT: —
- Step 3: 35.5 (#86)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Gemma 1.1 7b IT: 28.1 (#273)
- Step 3: 46.3 (#159)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Non-English | 1052 | 1327 |
| LMArena Chinese | 1061 | 1397 |
| LMArena German | 1054 | 1371 |
| LMArena Korean | 988 | 1269 |
| LMArena Russian | 1046 | 1331 |
| LMArena Spanish | 1049 | 1371 |
| LMArena French | 1065 | — |
| LMArena Japanese | 971 | — |

## Instruction Following

- Gemma 1.1 7b IT: 54.0 (#283)
- Step 3: 70.4 (#164)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1057 | 1332 |

## Long Context

- Gemma 1.1 7b IT: 32.1 (#272)
- Step 3: 40.3 (#157)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Longer Query | 1056 | 1326 |

## Writing & Preference

- Gemma 1.1 7b IT: 30.4 (#288)
- Step 3: 54.3 (#151)

| Benchmark | Gemma 1.1 7b IT | Step 3 |
|---|---|---|
| LMArena Text | 1094 | 1350 |
| LMArena Creative Writing | 1060 | 1321 |
| LMArena Multi-Turn | 1040 | 1341 |

## FAQ

### Is Gemma 1.1 7b IT better than Step 3?

Step 3 is the stronger model overall, scoring 40.5 to 31.3 on the Noometry Index.

### Is Gemma 1.1 7b IT or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 40.1 versus 31.5 in the Noometry coding category.

### How many benchmarks do Gemma 1.1 7b IT and Step 3 share?

15 benchmarks have published results for both models. Gemma 1.1 7b IT has 19 scored results on Noometry and Step 3 has 17.