Model comparison
Gemma 2B vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 29.1 on the Noometry Index.
Last verified . 11 shared benchmarks.
Google
StepFunSummary
- They share 11 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Step 2 16k Exp 202412 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 2 16k Exp 202412 leads 52.5 to 24.1.
- Gemma 2B has downloadable open weights; the other is API-only.
Side by side
| Gemma 2B | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 29.1 | 38.6 |
| Released | 2024-02-21 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Gemma 2B: 28.9 (#300), Step 2 16k Exp 202412: 37.9 (#170)
| Benchmark | Gemma 2B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1010 | 1316 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Step 2 16k Exp 202412 leads
Gemma 2B: 17.9 (#275), Step 2 16k Exp 202412: 24.8 (#140)
| Benchmark | Gemma 2B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 989 | 1299 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 93.57 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Step 2 16k Exp 202412 leads
Gemma 2B: 27.6 (#237), Step 2 16k Exp 202412: 33.6 (#171)
| Benchmark | Gemma 2B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1009 | 1305 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Step 2 16k Exp 202412: 34.6 (#187)
| Benchmark | Gemma 2B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | — | 1279 |
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Step 2 16k Exp 202412 leads
Gemma 2B: 23.1 (#289), Step 2 16k Exp 202412: 43.9 (#176)
| Benchmark | Gemma 2B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 958 | 1290 |
| LMArena Chinese | 986 | 1331 |
| LMArena Russian | 937 | 1324 |
Instruction Following Step 2 16k Exp 202412 leads
Gemma 2B: 48.8 (#297), Step 2 16k Exp 202412: 68.1 (#187)
| Benchmark | Gemma 2B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 971 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Gemma 2B: 29.9 (#286), Step 2 16k Exp 202412: 39.7 (#165)
| Benchmark | Gemma 2B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 981 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Gemma 2B: 24.1 (#303), Step 2 16k Exp 202412: 52.5 (#168)
| Benchmark | Gemma 2B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1002 | 1321 |
| LMArena Creative Writing | 986 | 1328 |
| LMArena Multi-Turn | 945 | 1292 |
Frequently asked questions
Is Gemma 2B better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 29.1 on the Noometry Index.
Is Gemma 2B or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 37.9 versus 28.9 in the Noometry coding category.
How many benchmarks do Gemma 2B and Step 2 16k Exp 202412 share?
11 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Step 2 16k Exp 202412 has 12.