Model comparison
Gemma 2 9B vs Gemma 3 27B
Gemma 3 27B is the stronger model overall, scoring 30.8 to 25.9 on the Noometry Index.
Last verified . 29 shared benchmarks.
GoogleSummary
- They share 29 benchmarks with published results for both. Gemma 2 9B scores higher in 2 categories and Gemma 3 27B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 32.1.
- The biggest single-benchmark swing is MATH Level 5: 21% for Gemma 2 9B and 74% for Gemma 3 27B.
Side by side
| Gemma 2 9B | Gemma 3 27B | |
|---|---|---|
| Provider | ||
| Noometry Index | 25.9 | 30.8 |
| Released | 2024-06-24 | 2025-03-11 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.16 |
| Results tracked | 35 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 2 9B leads
Gemma 2 9B: 29.4 (#304), Gemma 3 27B: 22.5 (#334)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| LiveBench Coding | 22.5% | 39.9% |
| LMArena Coding | 1173 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
| BigCodeBench Instruct | 34.7% | — |
| BigCodeBench Complete | 40.6% | — |
Agentic & Tool Use Not comparable
Gemma 2 9B: —, Gemma 3 27B: 25.1 (#110)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |
Reasoning Too close to call
Gemma 2 9B: 15.9 (#309), Gemma 3 27B: 16.7 (#301)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| LiveBench Reasoning | 15.2% | 43.8% |
| LMArena Hard Prompts | 1171 | 1340 |
| LiveBench Data Analysis | 36.4% | 51.5% |
| Epoch Capabilities Index | 119.83 | 130.04 |
| LiveBench | 28.7% | 50% |
| Kagi LLM Benchmark | — | 40.4% |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 52.5% |
| LMCA | — | 12.3% |
| PIQA | 83.7% | — |
Math Gemma 3 27B leads
Gemma 2 9B: 9.9 (#318), Gemma 3 27B: 25.9 (#265)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | 22.5% |
| LiveBench Math | 19.8% | 55.4% |
| LMArena Math | 1183 | 1312 |
| MATH Level 5 | 21% | 74% |
| GSM8K | 84.9% | — |
Knowledge Gemma 3 27B leads
Gemma 2 9B: 9.7 (#305), Gemma 3 27B: 25.5 (#261)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | 27.5% | 47.7% |
| LMArena Expert | 1147 | 1304 |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multimodal Not comparable
Gemma 2 9B: —, Gemma 3 27B: 32.6 (#100)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1164 |
| GeoBench | — | 52% |
Multilingual Gemma 3 27B leads
Gemma 2 9B: 36.6 (#238), Gemma 3 27B: 46.9 (#155)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1188 | 1334 |
| LMArena Chinese | 1185 | 1346 |
| LMArena French | 1190 | 1368 |
| LMArena German | 1186 | 1362 |
| LMArena Japanese | 1144 | 1287 |
| LMArena Korean | 1137 | 1308 |
| LMArena Russian | 1200 | 1349 |
| LMArena Spanish | 1200 | 1349 |
Instruction Following Gemma 3 27B leads
Gemma 2 9B: 57.6 (#269), Gemma 3 27B: 70.6 (#160)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| LiveBench Instruction Following | 52.6% | 74.9% |
| LMArena Instruction Following | 1178 | 1321 |
Long Context Gemma 2 9B leads
Gemma 2 9B: 36.3 (#233), Gemma 3 27B: 27.6 (#293)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1197 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Gemma 3 27B leads
Gemma 2 9B: 32.1 (#281), Gemma 3 27B: 52.5 (#168)
| Benchmark | Gemma 2 9B | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1207 | 1358 |
| LMArena Creative Writing | 1206 | 1346 |
| EQ-Bench Creative Writing | 841 | 1266 |
| LMArena Multi-Turn | 1193 | 1345 |
| LiveBench Language | 25.5% | 34.6% |
| Short-Story Creative Writing | — | 79.9% |
Frequently asked questions
Is Gemma 2 9B better than Gemma 3 27B?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Gemma 3 27B better for coding?
Gemma 2 9B scores higher on coding benchmarks: 29.4 versus 22.5 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Gemma 3 27B share?
29 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Gemma 3 27B has 43.