Model comparison
Gemma 3 12B vs Granite 3.0 2b Instruct
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
GoogleSummary
- They share 11 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Granite 3.0 2b Instruct in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.7 to 27.0.
Side by side
| Gemma 3 12B | Granite 3.0 2b Instruct | |
|---|---|---|
| Provider | IBM | |
| Noometry Index | 32.1 | 30.8 |
| 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 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 12B leads
Gemma 3 12B: 31.7 (#280), Granite 3.0 2b Instruct: 28.3 (#316)
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Coding | 1281 | 1090 |
| SciCode | 17.4% | — |
| BigCodeBench Instruct | — | 20.5% |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Granite 3.0 2b Instruct: —
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Granite 3.0 2b Instruct leads
Gemma 3 12B: 15.7 (#313), Granite 3.0 2b Instruct: 20.5 (#235)
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1073 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
Math Granite 3.0 2b Instruct leads
Gemma 3 12B: 22.3 (#279), Granite 3.0 2b Instruct: 32.2 (#217)
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Math | 1307 | 1117 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Granite 3.0 2b Instruct leads
Gemma 3 12B: 26.5 (#257), Granite 3.0 2b Instruct: 29.0 (#241)
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Expert | 1248 | 1064 |
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
Multimodal Not comparable
Gemma 3 12B: —, Granite 3.0 2b Instruct: —
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Granite 3.0 2b Instruct: 27.0 (#278)
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Non-English | 1318 | 1033 |
| LMArena Russian | 1335 | 1045 |
| LMArena Chinese | — | 1070 |
| LMArena German | 1370 | — |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.6 (#186), Granite 3.0 2b Instruct: 53.9 (#284)
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Instruction Following | 1299 | 1056 |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Granite 3.0 2b Instruct: 32.5 (#268)
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Longer Query | 1317 | 1070 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.5 (#209), Granite 3.0 2b Instruct: 29.6 (#292)
| Benchmark | Gemma 3 12B | Granite 3.0 2b Instruct |
|---|---|---|
| LMArena Text | 1334 | 1080 |
| LMArena Creative Writing | 1331 | 1046 |
| LMArena Multi-Turn | 1334 | 1053 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Granite 3.0 2b Instruct?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.
Is Gemma 3 12B or Granite 3.0 2b Instruct better for coding?
Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 28.3 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Granite 3.0 2b Instruct share?
11 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Granite 3.0 2b Instruct has 13.