Model comparison
Gemma 2 2b IT vs Gemma 3 12B
Gemma 2 2b IT and Gemma 3 12B score almost the same on the Noometry Index (33.1 vs 32.1), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
GoogleSummary
- They share 12 benchmarks with published results for both. Gemma 2 2b IT scores higher in 4 categories and Gemma 3 12B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.7 to 32.3.
Side by side
| Gemma 2 2b IT | Gemma 3 12B | |
|---|---|---|
| Provider | ||
| Noometry Index | 33.1 | 32.1 |
| 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 | 17 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2 2b IT: 32.3 (#273), Gemma 3 12B: 31.7 (#280)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1112 | 1281 |
| SciCode | — | 17.4% |
Agentic & Tool Use Not comparable
Gemma 2 2b IT: —, Gemma 3 12B: 25.5 (#108)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |
Reasoning Gemma 2 2b IT leads
Gemma 2 2b IT: 21.4 (#224), Gemma 3 12B: 15.7 (#313)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1113 | 1309 |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 48.8% |
| LMCA | — | 4.5% |
| Epoch Capabilities Index | — | 123.5 |
Math Gemma 2 2b IT leads
Gemma 2 2b IT: 32.6 (#212), Gemma 3 12B: 22.3 (#279)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| LMArena Math | 1135 | 1307 |
| OTIS Mock AIME 2024-2025 | — | 16.7% |
Knowledge Gemma 2 2b IT leads
Gemma 2 2b IT: 29.9 (#231), Gemma 3 12B: 26.5 (#257)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| LMArena Expert | 1096 | 1248 |
| GPQA Diamond | — | 39.5% |
| Vectara Hallucination Rate | — | 4.4% |
Multimodal Not comparable
Gemma 2 2b IT: —, Gemma 3 12B: —
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| MindCube | — | 46.7% |
Multilingual Gemma 3 12B leads
Gemma 2 2b IT: 32.3 (#257), Gemma 3 12B: 45.7 (#165)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1121 | 1318 |
| LMArena German | 1114 | 1370 |
| LMArena Russian | 1118 | 1335 |
| LMArena Chinese | 1132 | — |
| LMArena French | 1157 | — |
| LMArena Japanese | 1083 | — |
| LMArena Korean | 1055 | — |
| LMArena Spanish | 1140 | — |
Instruction Following Gemma 3 12B leads
Gemma 2 2b IT: 57.8 (#263), Gemma 3 12B: 68.6 (#186)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1118 | 1299 |
Long Context Gemma 3 12B leads
Gemma 2 2b IT: 34.3 (#250), Gemma 3 12B: 40.0 (#162)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1130 | 1317 |
Writing & Preference Gemma 3 12B leads
Gemma 2 2b IT: 36.5 (#263), Gemma 3 12B: 47.5 (#209)
| Benchmark | Gemma 2 2b IT | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1156 | 1334 |
| LMArena Creative Writing | 1147 | 1331 |
| LMArena Multi-Turn | 1118 | 1334 |
| EQ-Bench Creative Writing | — | 1126 |
Frequently asked questions
Is Gemma 2 2b IT better than Gemma 3 12B?
Gemma 2 2b IT and Gemma 3 12B score almost the same on the Noometry Index (33.1 vs 32.1), so choose on price, context window or the category you care about most.
Is Gemma 2 2b IT or Gemma 3 12B better for coding?
They score almost the same on coding (32.3 vs 31.7); test both on your own repository before choosing.
How many benchmarks do Gemma 2 2b IT and Gemma 3 12B share?
12 benchmarks have published results for both models. Gemma 2 2b IT has 17 scored results on Noometry and Gemma 3 12B has 24.