Model comparison
Gemma 7B vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 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 2 16k Exp 202412 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 2 16k Exp 202412 leads 52.3 to 27.1.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Gemma 7B | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 30.0 | 39.2 |
| Released | 2024-02-21 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 27 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Gemma 7B: 30.5 (#294), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Gemma 7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1048 | 1316 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Step 2 16k Exp 202412 leads
Gemma 7B: 19.9 (#249), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Gemma 7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1299 |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.99 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Step 2 16k Exp 202412 leads
Gemma 7B: 31.2 (#228), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Gemma 7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1066 | 1304 |
| GSM8K | 46.4% | — |
Knowledge Step 2 16k Exp 202412 leads
Gemma 7B: 27.3 (#252), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Gemma 7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1001 | 1279 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Step 2 16k Exp 202412 leads
Gemma 7B: 25.1 (#287), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Gemma 7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 999 | 1290 |
| LMArena Chinese | 1035 | 1331 |
| LMArena Russian | 993 | 1324 |
| LMArena French | 1025 | — |
Instruction Following Step 2 16k Exp 202412 leads
Gemma 7B: 51.5 (#295), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Gemma 7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1017 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Gemma 7B: 31.1 (#282), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Gemma 7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1022 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Gemma 7B: 27.1 (#302), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Gemma 7B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1056 | 1321 |
| LMArena Creative Writing | 1024 | 1328 |
| LMArena Multi-Turn | 963 | 1292 |
Frequently asked questions
Is Gemma 7B better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 30.0 on the Noometry Index.
Is Gemma 7B or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Step 2 16k Exp 202412 has 12.