Model comparison
Gemma 2 9B vs Granite 4.0 H Small
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 25.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
GoogleSummary
- They share 13 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Granite 4.0 H Small in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.0 H Small leads 32.0 to 9.7.
Side by side
| Gemma 2 9B | Granite 4.0 H Small | |
|---|---|---|
| Provider | IBM | |
| Noometry Index | 25.9 | 36.5 |
| Released | 2024-06-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.0 H Small leads
Gemma 2 9B: 29.4 (#304), Granite 4.0 H Small: 36.4 (#209)
| Benchmark | Gemma 2 9B | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1173 | 1249 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Granite 4.0 H Small leads
Gemma 2 9B: 15.9 (#309), Granite 4.0 H Small: 24.4 (#163)
| Benchmark | Gemma 2 9B | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1240 |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Granite 4.0 H Small leads
Gemma 2 9B: 9.9 (#318), Granite 4.0 H Small: 31.4 (#223)
| Benchmark | Gemma 2 9B | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1183 | 1247 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| Omni-MATH | — | 29.6% |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Granite 4.0 H Small leads
Gemma 2 9B: 9.7 (#305), Granite 4.0 H Small: 32.0 (#215)
| Benchmark | Gemma 2 9B | Granite 4.0 H Small |
|---|---|---|
| LMArena Expert | 1147 | 1251 |
| GPQA Diamond | 27.5% | — |
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual Granite 4.0 H Small leads
Gemma 2 9B: 36.6 (#238), Granite 4.0 H Small: 38.6 (#228)
| Benchmark | Gemma 2 9B | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1188 | 1216 |
| LMArena Chinese | 1185 | 1249 |
| LMArena Russian | 1200 | 1201 |
| LMArena Spanish | 1200 | 1258 |
| LMArena French | 1190 | — |
| LMArena German | 1186 | — |
| LMArena Japanese | 1144 | — |
| LMArena Korean | 1137 | — |
Instruction Following Granite 4.0 H Small leads
Gemma 2 9B: 57.6 (#269), Granite 4.0 H Small: 68.7 (#183)
| Benchmark | Gemma 2 9B | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1178 | 1222 |
| LiveBench Instruction Following | 52.6% | — |
| IFEval | — | 89% |
Long Context Granite 4.0 H Small leads
Gemma 2 9B: 36.3 (#233), Granite 4.0 H Small: 37.7 (#213)
| Benchmark | Gemma 2 9B | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1197 | 1242 |
Writing & Preference Granite 4.0 H Small leads
Gemma 2 9B: 32.1 (#281), Granite 4.0 H Small: 43.8 (#227)
| Benchmark | Gemma 2 9B | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1207 | 1241 |
| LMArena Creative Writing | 1206 | 1211 |
| LMArena Multi-Turn | 1193 | 1242 |
| EQ-Bench Creative Writing | 841 | — |
| WildBench | — | 73.9% |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Granite 4.0 H Small?
Granite 4.0 H Small is the stronger model overall, scoring 36.5 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Granite 4.0 H Small better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 36.4 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Granite 4.0 H Small share?
13 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Granite 4.0 H Small has 19.