Model comparison
Gemma 3 27B vs Llama 3.2 3B
Gemma 3 27B is the stronger model overall, scoring 30.8 to 28.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
Google
MetaSummary
- They share 15 benchmarks with published results for both. Gemma 3 27B scores higher in 4 categories and Llama 3.2 3B in 5 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 24.7.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 29.5% for Gemma 3 27B and 21.9% for Llama 3.2 3B.
- Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $0.05 / $0.33 for Llama 3.2 3B.
Side by side
| Gemma 3 27B | Llama 3.2 3B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 28.9 |
| Released | 2025-03-11 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 131K | 131K |
| Max output | 8K | 118K |
| Input $ / M tokens | $0.08 | $0.05 |
| Output $ / M tokens | $0.16 | $0.33 |
| Results tracked | 43 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.2 3B leads
Gemma 3 27B: 22.5 (#334), Llama 3.2 3B: 27.6 (#319)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Coding | 1322 | 1098 |
| Aider Polyglot | 4.9% | — |
| SciCode | 21.2% | — |
| BigCodeBench Instruct | — | 23.4% |
| LiveBench Coding | 39.9% | — |
| BigCodeBench Complete | — | 28.3% |
Agentic & Tool Use Gemma 3 27B leads
Gemma 3 27B: 25.1 (#110), Llama 3.2 3B: 20.1 (#143)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 29.5% | 21.9% |
| BALROG | — | 10.1% |
Reasoning Llama 3.2 3B leads
Gemma 3 27B: 16.7 (#301), Llama 3.2 3B: 21.0 (#228)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1340 | 1095 |
| Kagi LLM Benchmark | 40.4% | — |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 43.8% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 51.5% | — |
| LMCA | 12.3% | — |
| Epoch Capabilities Index | 130.04 | — |
| LiveBench | 50% | — |
Math Llama 3.2 3B leads
Gemma 3 27B: 25.9 (#265), Llama 3.2 3B: 32.4 (#214)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1312 | 1126 |
| OTIS Mock AIME 2024-2025 | 22.5% | — |
| LiveBench Math | 55.4% | — |
| MATH Level 5 | 74% | — |
Knowledge Llama 3.2 3B leads
Gemma 3 27B: 25.5 (#261), Llama 3.2 3B: 29.7 (#235)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1304 | 1090 |
| GPQA Diamond | 47.7% | — |
| Confabulations | 40.3% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multimodal Not comparable
Gemma 3 27B: 32.6 (#100), Llama 3.2 3B: —
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Vision | 1164 | — |
| GeoBench | 52% | — |
Multilingual Gemma 3 27B leads
Gemma 3 27B: 46.9 (#155), Llama 3.2 3B: 26.2 (#281)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1334 | 1019 |
| LMArena Chinese | 1346 | 1017 |
| LMArena German | 1362 | 1056 |
| LMArena Russian | 1349 | 949 |
| LMArena French | 1368 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1349 | — |
Instruction Following Gemma 3 27B leads
Gemma 3 27B: 70.6 (#160), Llama 3.2 3B: 56.0 (#275)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1321 | 1089 |
| LiveBench Instruction Following | 74.9% | — |
Long Context Llama 3.2 3B leads
Gemma 3 27B: 27.6 (#293), Llama 3.2 3B: 33.4 (#261)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1333 | 1100 |
| Fiction.LiveBench | 33.3% | — |
Writing & Preference Gemma 3 27B leads
Gemma 3 27B: 52.5 (#168), Llama 3.2 3B: 24.7 (#307)
| Benchmark | Gemma 3 27B | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1358 | 1110 |
| LMArena Creative Writing | 1346 | 1094 |
| EQ-Bench Creative Writing | 1266 | 595 |
| LMArena Multi-Turn | 1345 | 1105 |
| Short-Story Creative Writing | 79.9% | — |
| LiveBench Language | 34.6% | — |
Frequently asked questions
Is Gemma 3 27B better than Llama 3.2 3B?
Gemma 3 27B is the stronger model overall, scoring 30.8 to 28.9 on the Noometry Index.
Which is cheaper, Gemma 3 27B or Llama 3.2 3B?
Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Llama 3.2 3B lists at $0.05 and $0.33.
Is Gemma 3 27B or Llama 3.2 3B better for coding?
Llama 3.2 3B scores higher on coding benchmarks: 27.6 versus 22.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 131K tokens.
How many benchmarks do Gemma 3 27B and Llama 3.2 3B share?
15 benchmarks have published results for both models. Gemma 3 27B has 43 scored results on Noometry and Llama 3.2 3B has 18.