Model comparison
Gemma 2 9B vs Granite 3.0 8b Instruct
Granite 3.0 8b Instruct is the stronger model overall, scoring 31.6 to 25.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
GoogleSummary
- They share 14 benchmarks with published results for both. Gemma 2 9B scores higher in 4 categories and Granite 3.0 8b Instruct in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.0 8b Instruct leads 32.8 to 9.9.
- The biggest single-benchmark swing is BigCodeBench Instruct: 34.7% for Gemma 2 9B and 29.3% for Granite 3.0 8b Instruct.
Side by side
| Gemma 2 9B | Granite 3.0 8b Instruct | |
|---|---|---|
| Provider | IBM | |
| Noometry Index | 25.9 | 31.6 |
| Released | 2024-06-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 14 |
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), Granite 3.0 8b Instruct: 29.7 (#301)
| Benchmark | Gemma 2 9B | Granite 3.0 8b Instruct |
|---|---|---|
| BigCodeBench Instruct | 34.7% | 29.3% |
| LMArena Coding | 1173 | 1112 |
| BigCodeBench Complete | 40.6% | 35.4% |
| LiveBench Coding | 22.5% | — |
Reasoning Granite 3.0 8b Instruct leads
Gemma 2 9B: 15.9 (#309), Granite 3.0 8b Instruct: 20.9 (#230)
| Benchmark | Gemma 2 9B | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1092 |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Granite 3.0 8b Instruct leads
Gemma 2 9B: 9.9 (#318), Granite 3.0 8b Instruct: 32.8 (#210)
| Benchmark | Gemma 2 9B | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Math | 1183 | 1143 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Granite 3.0 8b Instruct leads
Gemma 2 9B: 9.7 (#305), Granite 3.0 8b Instruct: 29.6 (#236)
| Benchmark | Gemma 2 9B | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Expert | 1147 | 1087 |
| GPQA Diamond | 27.5% | — |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual Gemma 2 9B leads
Gemma 2 9B: 36.6 (#238), Granite 3.0 8b Instruct: 27.2 (#276)
| Benchmark | Gemma 2 9B | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Non-English | 1188 | 1037 |
| LMArena Chinese | 1185 | 1063 |
| LMArena Russian | 1200 | 1060 |
| 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), Granite 3.0 8b Instruct: 56.0 (#276)
| Benchmark | Gemma 2 9B | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Instruction Following | 1178 | 1088 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), Granite 3.0 8b Instruct: 34.0 (#252)
| Benchmark | Gemma 2 9B | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Longer Query | 1197 | 1122 |
Writing & Preference Gemma 2 9B leads
Gemma 2 9B: 32.1 (#281), Granite 3.0 8b Instruct: 31.1 (#285)
| Benchmark | Gemma 2 9B | Granite 3.0 8b Instruct |
|---|---|---|
| LMArena Text | 1207 | 1096 |
| LMArena Creative Writing | 1206 | 1071 |
| LMArena Multi-Turn | 1193 | 1063 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Granite 3.0 8b Instruct?
Granite 3.0 8b Instruct is the stronger model overall, scoring 31.6 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Granite 3.0 8b Instruct better for coding?
They score almost the same on coding (29.4 vs 29.7); test both on your own repository before choosing.
How many benchmarks do Gemma 2 9B and Granite 3.0 8b Instruct share?
14 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Granite 3.0 8b Instruct has 14.