Model comparison
Gemma 3 12B vs Granite 4.0 H Small
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 31.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 3 12B scores higher in 3 categories and Granite 4.0 H Small in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 4.0 H Small leads 29.3 to 21.0.
Side by side
| Gemma 3 12B | Granite 4.0 H Small | |
|---|---|---|
| Provider | IBM | |
| Noometry Index | 31.8 | 35.9 |
| Released | 2025-03-12 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.0 H Small leads
Gemma 3 12B: 31.2 (#276), Granite 4.0 H Small: 35.8 (#207)
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| LMArena Coding | 1281 | 1247 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Granite 4.0 H Small: —
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Granite 4.0 H Small leads
Gemma 3 12B: 15.2 (#307), Granite 4.0 H Small: 23.4 (#164)
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1240 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |
Math Granite 4.0 H Small leads
Gemma 3 12B: 21.0 (#273), Granite 4.0 H Small: 29.3 (#219)
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| LMArena Math | 1307 | 1251 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| Omni-MATH | — | 29.6% |
Knowledge Granite 4.0 H Small leads
Gemma 3 12B: 26.5 (#250), Granite 4.0 H Small: 31.5 (#210)
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| Vectara Hallucination Rate | 4.4% | 5.2% |
| LMArena Expert | 1248 | 1244 |
| GPQA Diamond | 39.5% | — |
| MMLU-Pro | — | 56.9% |
| GPQA (HELM) | — | 38.3% |
Multimodal Not comparable
Gemma 3 12B: —, Granite 4.0 H Small: —
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.9 (#160), Granite 4.0 H Small: 38.7 (#223)
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | 1318 | 1216 |
| LMArena Russian | 1335 | 1198 |
| LMArena Chinese | — | 1250 |
| LMArena German | 1370 | — |
| LMArena Spanish | — | 1258 |
Instruction Following Too close to call
Gemma 3 12B: 68.8 (#179), Granite 4.0 H Small: 68.9 (#178)
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| LMArena Instruction Following | 1299 | 1221 |
| IFEval | — | 89% |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#157), Granite 4.0 H Small: 37.6 (#209)
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | 1317 | 1240 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.7 (#205), Granite 4.0 H Small: 44.0 (#222)
| Benchmark | Gemma 3 12B | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | 1334 | 1241 |
| LMArena Creative Writing | 1331 | 1210 |
| LMArena Multi-Turn | 1334 | 1243 |
| EQ-Bench Creative Writing | 1126 | — |
| WildBench | — | 73.9% |
Frequently asked questions
Is Gemma 3 12B better than Granite 4.0 H Small?
Granite 4.0 H Small is the stronger model overall, scoring 35.9 to 31.8 on the Noometry Index.
Is Gemma 3 12B or Granite 4.0 H Small better for coding?
Granite 4.0 H Small scores higher on coding benchmarks: 35.8 versus 31.2 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Granite 4.0 H Small share?
12 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Granite 4.0 H Small has 19.