Model comparison
Gemma 2 9B vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 25.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
Google
StepFunSummary
- They share 15 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Step 3 leads 36.2 to 9.7.
Side by side
| Gemma 2 9B | Step 3 | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 25.7 | 39.9 |
| Released | 2024-06-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Gemma 2 9B: 29.0 (#299), Step 3: 39.5 (#144)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Coding | 1174 | 1367 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Step 3 leads
Gemma 2 9B: 15.3 (#306), Step 3: 27.6 (#102)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1172 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.78 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Step 3 leads
Gemma 2 9B: 9.3 (#312), Step 3: 34.9 (#148)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Math | 1183 | 1366 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Step 3 leads
Gemma 2 9B: 9.7 (#300), Step 3: 36.2 (#161)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Expert | 1147 | 1333 |
| GPQA Diamond | 27.5% | — |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, Step 3: 34.9 (#81)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Step 3 leads
Gemma 2 9B: 36.8 (#233), Step 3: 46.5 (#154)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Non-English | 1188 | 1327 |
| LMArena Chinese | 1185 | 1396 |
| LMArena German | 1186 | 1371 |
| LMArena Korean | 1137 | 1271 |
| LMArena Russian | 1200 | 1331 |
| LMArena Spanish | 1200 | 1372 |
| LMArena French | 1189 | — |
| LMArena Japanese | 1144 | — |
Instruction Following Step 3 leads
Gemma 2 9B: 57.8 (#264), Step 3: 70.6 (#159)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1178 | 1332 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Step 3 leads
Gemma 2 9B: 36.3 (#228), Step 3: 40.3 (#152)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1197 | 1326 |
Writing & Preference Step 3 leads
Gemma 2 9B: 32.3 (#276), Step 3: 54.5 (#146)
| Benchmark | Gemma 2 9B | Step 3 |
|---|---|---|
| LMArena Text | 1207 | 1351 |
| LMArena Creative Writing | 1206 | 1322 |
| LMArena Multi-Turn | 1193 | 1340 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 25.7 on the Noometry Index.
Is Gemma 2 9B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 29.0 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Step 3 share?
15 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Step 3 has 17.