Model comparison
Gemma 7B vs Step 1o Turbo 202506
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 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 1o Turbo 202506 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 1o Turbo 202506 leads 53.1 to 27.1.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Gemma 7B | Step 1o Turbo 202506 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 30.0 | 39.7 |
| Released | 2024-02-21 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 1o Turbo 202506 leads
Gemma 7B: 30.5 (#294), Step 1o Turbo 202506: 39.2 (#160)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Coding | 1048 | 1339 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Step 1o Turbo 202506 leads
Gemma 7B: 19.9 (#249), Step 1o Turbo 202506: 26.8 (#129)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1335 |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.99 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Step 1o Turbo 202506 leads
Gemma 7B: 31.2 (#228), Step 1o Turbo 202506: 36.6 (#164)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Math | 1066 | 1318 |
| GSM8K | 46.4% | — |
Knowledge Step 1o Turbo 202506 leads
Gemma 7B: 27.3 (#252), Step 1o Turbo 202506: 36.1 (#176)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Expert | 1001 | 1308 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multimodal Not comparable
Gemma 7B: —, Step 1o Turbo 202506: 36.1 (#80)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Vision | — | 1186 |
Multilingual Step 1o Turbo 202506 leads
Gemma 7B: 25.1 (#287), Step 1o Turbo 202506: 45.3 (#173)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Non-English | 999 | 1313 |
| LMArena Chinese | 1035 | 1380 |
| LMArena Russian | 993 | 1327 |
| LMArena French | 1025 | — |
| LMArena German | — | 1314 |
Instruction Following Step 1o Turbo 202506 leads
Gemma 7B: 51.5 (#295), Step 1o Turbo 202506: 69.2 (#176)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Instruction Following | 1017 | 1310 |
Long Context Step 1o Turbo 202506 leads
Gemma 7B: 31.1 (#282), Step 1o Turbo 202506: 41.0 (#146)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Longer Query | 1022 | 1348 |
Writing & Preference Step 1o Turbo 202506 leads
Gemma 7B: 27.1 (#302), Step 1o Turbo 202506: 53.1 (#160)
| Benchmark | Gemma 7B | Step 1o Turbo 202506 |
|---|---|---|
| LMArena Text | 1056 | 1336 |
| LMArena Creative Writing | 1024 | 1307 |
| LMArena Multi-Turn | 963 | 1340 |
Frequently asked questions
Is Gemma 7B better than Step 1o Turbo 202506?
Step 1o Turbo 202506 is the stronger model overall, scoring 39.7 to 30.0 on the Noometry Index.
Is Gemma 7B or Step 1o Turbo 202506 better for coding?
Step 1o Turbo 202506 scores higher on coding benchmarks: 39.2 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Step 1o Turbo 202506 share?
12 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Step 1o Turbo 202506 has 14.