Model comparison
Gemma 7B vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Google
StepFunSummary
- They share 12 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Step 5 Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 5 Preview leads 62.8 to 27.1.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Gemma 7B | Step 5 Preview | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 30.0 | 47.9 |
| Released | 2024-02-21 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 27 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Gemma 7B: 30.5 (#294), Step 5 Preview: 51.8 (#36)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1048 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Step 5 Preview leads
Gemma 7B: 19.9 (#249), Step 5 Preview: 40.0 (#57)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1465 |
| CritPt | — | 20.9% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.99 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Step 5 Preview leads
Gemma 7B: 31.2 (#228), Step 5 Preview: 46.1 (#72)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Math | 1066 | 1470 |
| ProofBench | — | 42% |
| GSM8K | 46.4% | — |
Knowledge Step 5 Preview leads
Gemma 7B: 27.3 (#252), Step 5 Preview: 41.2 (#112)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1001 | 1470 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multimodal Not comparable
Gemma 7B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Gemma 7B: 25.1 (#287), Step 5 Preview: 53.8 (#54)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 999 | 1432 |
| LMArena Chinese | 1035 | 1519 |
| LMArena Russian | 993 | 1436 |
| LMArena French | 1025 | — |
| LMArena Spanish | — | 1439 |
Instruction Following Step 5 Preview leads
Gemma 7B: 51.5 (#295), Step 5 Preview: 76.0 (#50)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1017 | 1444 |
Long Context Step 5 Preview leads
Gemma 7B: 31.1 (#282), Step 5 Preview: 44.5 (#64)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1022 | 1455 |
Writing & Preference Step 5 Preview leads
Gemma 7B: 27.1 (#302), Step 5 Preview: 62.8 (#71)
| Benchmark | Gemma 7B | Step 5 Preview |
|---|---|---|
| LMArena Text | 1056 | 1442 |
| LMArena Creative Writing | 1024 | 1410 |
| LMArena Multi-Turn | 963 | 1447 |
Frequently asked questions
Is Gemma 7B better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 30.0 on the Noometry Index.
Is Gemma 7B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Step 5 Preview share?
12 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Step 5 Preview has 18.