Model comparison
Gemma 3 12B vs Gemma 3 27B
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.
Last verified . 23 shared benchmarks.
GoogleSummary
- They share 23 benchmarks with published results for both. Gemma 3 12B scores higher in 4 categories and Gemma 3 27B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Gemma 3 12B leads 40.0 to 27.6.
- The biggest single-benchmark swing is GPQA Diamond: 39.5% for Gemma 3 12B and 47.7% for Gemma 3 27B.
- Gemma 3 12B is cheaper at $0.05 / $0.15 per million input/output tokens, against $0.08 / $0.16 for Gemma 3 27B.
Side by side
| Gemma 3 12B | Gemma 3 27B | |
|---|---|---|
| Provider | ||
| Noometry Index | 32.1 | 30.8 |
| Released | 2025-03-12 | 2025-03-11 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 8K |
| Input $ / M tokens | $0.05 | $0.08 |
| Output $ / M tokens | $0.15 | $0.16 |
| Results tracked | 24 | 43 |
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), Gemma 3 27B: 22.5 (#334)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| SciCode | 17.4% | 21.2% |
| LMArena Coding | 1281 | 1322 |
| Aider Polyglot | — | 4.9% |
| LiveBench Coding | — | 39.9% |
Agentic & Tool Use Too close to call
Gemma 3 12B: 25.5 (#108), Gemma 3 27B: 25.1 (#110)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | 29.5% |
Reasoning Gemma 3 27B leads
Gemma 3 12B: 15.7 (#313), Gemma 3 27B: 16.7 (#301)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| CritPt | 0% | 0% |
| Chess Puzzles | 0% | 0% |
| LMArena Hard Prompts | 1309 | 1340 |
| DTBench | 48.8% | 52.5% |
| LMCA | 4.5% | 12.3% |
| Epoch Capabilities Index | 123.5 | 130.04 |
| Kagi LLM Benchmark | — | 40.4% |
| LiveBench Reasoning | — | 43.8% |
| LiveBench Data Analysis | — | 51.5% |
| LiveBench | — | 50% |
Math Gemma 3 27B leads
Gemma 3 12B: 22.3 (#279), Gemma 3 27B: 25.9 (#265)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | 22.5% |
| LMArena Math | 1307 | 1312 |
| LiveBench Math | — | 55.4% |
| MATH Level 5 | — | 74% |
Knowledge Gemma 3 12B leads
Gemma 3 12B: 26.5 (#257), Gemma 3 27B: 25.5 (#261)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | 39.5% | 47.7% |
| Vectara Hallucination Rate | 4.4% | 7.4% |
| LMArena Expert | 1248 | 1304 |
| Confabulations | — | 40.3% |
Multimodal Not comparable
Gemma 3 12B: —, Gemma 3 27B: 32.6 (#100)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1164 |
| GeoBench | — | 52% |
| MindCube | 46.7% | — |
Multilingual Gemma 3 27B leads
Gemma 3 12B: 45.7 (#165), Gemma 3 27B: 46.9 (#155)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1318 | 1334 |
| LMArena German | 1370 | 1362 |
| LMArena Russian | 1335 | 1349 |
| LMArena Chinese | — | 1346 |
| LMArena French | — | 1368 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1308 |
| LMArena Spanish | — | 1349 |
Instruction Following Gemma 3 27B leads
Gemma 3 12B: 68.6 (#186), Gemma 3 27B: 70.6 (#160)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1299 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
Long Context Gemma 3 12B leads
Gemma 3 12B: 40.0 (#162), Gemma 3 27B: 27.6 (#293)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1317 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Gemma 3 27B leads
Gemma 3 12B: 47.5 (#209), Gemma 3 27B: 52.5 (#168)
| Benchmark | Gemma 3 12B | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1334 | 1358 |
| LMArena Creative Writing | 1331 | 1346 |
| EQ-Bench Creative Writing | 1126 | 1266 |
| LMArena Multi-Turn | 1334 | 1345 |
| Short-Story Creative Writing | — | 79.9% |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is Gemma 3 12B better than Gemma 3 27B?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.
Which is cheaper, Gemma 3 12B or Gemma 3 27B?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Gemma 3 27B lists at $0.08 and $0.16.
Is Gemma 3 12B or Gemma 3 27B better for coding?
Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Gemma 3 12B and Gemma 3 27B share?
23 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Gemma 3 27B has 43.