Model comparison
Gemma 3 12B vs Palm 2
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.0 on the Noometry Index.
Last verified . 9 shared benchmarks.
GoogleSummary
- They share 9 benchmarks with published results for both. Gemma 3 12B scores higher in 5 categories and Palm 2 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.7 to 20.9.
- Gemma 3 12B has downloadable open weights; the other is API-only.
Side by side
| Gemma 3 12B | Palm 2 | |
|---|---|---|
| Provider | ||
| Noometry Index | 32.1 | 30.0 |
| Released | 2025-03-12 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 24 | 10 |
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), Palm 2: 29.0 (#311)
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| LMArena Coding | 1281 | 994 |
| SciCode | 17.4% | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.5 (#108), Palm 2: —
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Palm 2 leads
Gemma 3 12B: 15.7 (#313), Palm 2: 19.1 (#271)
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1309 | 1005 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.5 | — |
Math Palm 2 leads
Gemma 3 12B: 22.3 (#279), Palm 2: 30.8 (#231)
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| LMArena Math | 1307 | 1049 |
| OTIS Mock AIME 2024-2025 | 16.7% | — |
Knowledge Not comparable
Gemma 3 12B: 26.5 (#257), Palm 2: —
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |
Multimodal Not comparable
Gemma 3 12B: —, Palm 2: —
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Gemma 3 12B leads
Gemma 3 12B: 45.7 (#165), Palm 2: 20.9 (#295)
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| LMArena Non-English | 1318 | 916 |
| LMArena Chinese | — | 887 |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |
Instruction Following Gemma 3 12B leads
Gemma 3 12B: 68.6 (#186), Palm 2: 51.0 (#296)
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1299 | 1010 |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Palm 2: 30.8 (#285)
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1317 | 1010 |
Writing & Preference Gemma 3 12B leads
Gemma 3 12B: 47.5 (#209), Palm 2: 25.6 (#304)
| Benchmark | Gemma 3 12B | Palm 2 |
|---|---|---|
| LMArena Text | 1334 | 1027 |
| LMArena Creative Writing | 1331 | 991 |
| LMArena Multi-Turn | 1334 | 994 |
| EQ-Bench Creative Writing | 1126 | — |
Frequently asked questions
Is Gemma 3 12B better than Palm 2?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.0 on the Noometry Index.
Is Gemma 3 12B or Palm 2 better for coding?
Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 29.0 in the Noometry coding category.
How many benchmarks do Gemma 3 12B and Palm 2 share?
9 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Palm 2 has 10.