Model comparison
Gemma 2 9B vs Gemma 2B
Gemma 2B is the stronger model overall, scoring 29.6 to 25.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
GoogleSummary
- They share 16 benchmarks with published results for both. Gemma 2 9B scores higher in 5 categories and Gemma 2B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 2B leads 30.0 to 9.9.
Side by side
| Gemma 2 9B | Gemma 2B | |
|---|---|---|
| Provider | ||
| Noometry Index | 25.9 | 29.6 |
| Released | 2024-06-24 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 9B: 29.4 (#304), Gemma 2B: 29.4 (#305)
| Benchmark | Gemma 2 9B | Gemma 2B |
|---|---|---|
| LMArena Coding | 1173 | 1010 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Reasoning Gemma 2B leads
Gemma 2 9B: 15.9 (#309), Gemma 2B: 18.8 (#275)
| Benchmark | Gemma 2 9B | Gemma 2B |
|---|---|---|
| LMArena Hard Prompts | 1171 | 989 |
| Epoch Capabilities Index | 119.83 | 94.2 |
| PIQA | 83.7% | 77.3% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| BIG-Bench Hard | — | 35.2% |
| HellaSwag | — | 71.4% |
| LiveBench | 28.7% | — |
| WinoGrande | — | 65.4% |
Math Gemma 2B leads
Gemma 2 9B: 9.9 (#318), Gemma 2B: 30.0 (#239)
| Benchmark | Gemma 2 9B | Gemma 2B |
|---|---|---|
| LMArena Math | 1183 | 1009 |
| GSM8K | 84.9% | 17.7% |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
Knowledge Not comparable
Gemma 2 9B: 9.7 (#305), Gemma 2B: —
| Benchmark | Gemma 2 9B | Gemma 2B |
|---|---|---|
| BoolQ | 85.7% | 69.4% |
| MMLU | 72.1% | 42.3% |
| GPQA Diamond | 27.5% | — |
| LMArena Expert | 1147 | — |
| ARC (AI2) Challenge | — | 42.1% |
| TriviaQA | — | 53.2% |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Gemma 2B: 23.0 (#294)
| Benchmark | Gemma 2 9B | Gemma 2B |
|---|---|---|
| LMArena Non-English | 1188 | 958 |
| LMArena Chinese | 1185 | 986 |
| LMArena Russian | 1200 | 937 |
| LMArena French | 1190 | — |
| LMArena German | 1186 | — |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |
| LMArena Spanish | 1200 | — |
Instruction Following Gemma 2 9B leads
Gemma 2 9B: 57.6 (#269), Gemma 2B: 48.5 (#302)
| Benchmark | Gemma 2 9B | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | 1178 | 970 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), Gemma 2B: 29.9 (#291)
| Benchmark | Gemma 2 9B | Gemma 2B |
|---|---|---|
| LMArena Longer Query | 1197 | 981 |
Writing & Preference Gemma 2 9B leads
Gemma 2 9B: 32.1 (#281), Gemma 2B: 24.0 (#308)
| Benchmark | Gemma 2 9B | Gemma 2B |
|---|---|---|
| LMArena Text | 1207 | 1002 |
| LMArena Creative Writing | 1206 | 987 |
| LMArena Multi-Turn | 1193 | 945 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Gemma 2B?
Gemma 2B is the stronger model overall, scoring 29.6 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Gemma 2B better for coding?
They score almost the same on coding (29.4 vs 29.4); test both on your own repository before choosing.
How many benchmarks do Gemma 2 9B and Gemma 2B share?
16 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Gemma 2B has 23.