Model comparison
Gemma 2 9B vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 25.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
StepFunSummary
- They share 17 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Step 3.5 Flash in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3.5 Flash leads 42.6 to 9.9.
Side by side
| Gemma 2 9B | Step 3.5 Flash | |
|---|---|---|
| Provider | StepFun | |
| Noometry Index | 25.9 | 42.3 |
| Released | 2024-06-24 | 2026-01-29 |
| Weights | Open | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 35 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Gemma 2 9B: 29.4 (#304), Step 3.5 Flash: 42.4 (#105)
| Benchmark | Gemma 2 9B | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1173 | 1436 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Step 3.5 Flash leads
Gemma 2 9B: 15.9 (#309), Step 3.5 Flash: 22.2 (#202)
| Benchmark | Gemma 2 9B | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Step 3.5 Flash leads
Gemma 2 9B: 9.9 (#318), Step 3.5 Flash: 42.6 (#84)
| Benchmark | Gemma 2 9B | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1183 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Step 3.5 Flash leads
Gemma 2 9B: 9.7 (#305), Step 3.5 Flash: 39.6 (#132)
| Benchmark | Gemma 2 9B | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1147 | 1421 |
| GPQA Diamond | 27.5% | — |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual Step 3.5 Flash leads
Gemma 2 9B: 36.6 (#238), Step 3.5 Flash: 50.5 (#119)
| Benchmark | Gemma 2 9B | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1188 | 1385 |
| LMArena Chinese | 1185 | 1447 |
| LMArena French | 1190 | 1421 |
| LMArena German | 1186 | 1405 |
| LMArena Japanese | 1144 | 1354 |
| LMArena Korean | 1137 | 1352 |
| LMArena Russian | 1200 | 1385 |
| LMArena Spanish | 1200 | 1419 |
Instruction Following Step 3.5 Flash leads
Gemma 2 9B: 57.6 (#269), Step 3.5 Flash: 73.1 (#124)
| Benchmark | Gemma 2 9B | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1178 | 1385 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Step 3.5 Flash leads
Gemma 2 9B: 36.3 (#233), Step 3.5 Flash: 42.8 (#117)
| Benchmark | Gemma 2 9B | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1197 | 1402 |
Writing & Preference Step 3.5 Flash leads
Gemma 2 9B: 32.1 (#281), Step 3.5 Flash: 58.8 (#113)
| Benchmark | Gemma 2 9B | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1207 | 1403 |
| LMArena Creative Writing | 1206 | 1357 |
| LMArena Multi-Turn | 1193 | 1405 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 42.3 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Step 3.5 Flash share?
17 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Step 3.5 Flash has 19.