Model comparison
Codellama 34b Instruct vs Gemma 3 12B
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
GoogleSummary
- They share 9 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Gemma 3 12B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Gemma 3 12B leads 45.7 to 25.8.
Side by side
| Codellama 34b Instruct | Gemma 3 12B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 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 | 14 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Gemma 3 12B leads
Codellama 34b Instruct: 28.5 (#314), Gemma 3 12B: 31.7 (#280)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| LMArena Coding | 1046 | 1281 |
| SciCode | — | 17.4% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Gemma 3 12B: 25.5 (#108)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 30.4% |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Gemma 3 12B: 15.7 (#313)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1309 |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| DTBench | — | 48.8% |
| LMCA | — | 4.5% |
| Epoch Capabilities Index | — | 123.5 |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Gemma 3 12B: 22.3 (#279)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| LMArena Math | 1056 | 1307 |
| OTIS Mock AIME 2024-2025 | — | 16.7% |
Knowledge Not comparable
Codellama 34b Instruct: —, Gemma 3 12B: 26.5 (#257)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| GPQA Diamond | — | 39.5% |
| Vectara Hallucination Rate | — | 4.4% |
| LMArena Expert | — | 1248 |
Multimodal Not comparable
Codellama 34b Instruct: —, Gemma 3 12B: —
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| MindCube | — | 46.7% |
Multilingual Gemma 3 12B leads
Codellama 34b Instruct: 25.8 (#284), Gemma 3 12B: 45.7 (#165)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| LMArena Non-English | 1011 | 1318 |
| LMArena Chinese | 976 | — |
| LMArena German | — | 1370 |
| LMArena Russian | — | 1335 |
Instruction Following Gemma 3 12B leads
Codellama 34b Instruct: 52.2 (#291), Gemma 3 12B: 68.6 (#186)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1299 |
Long Context Gemma 3 12B leads
Codellama 34b Instruct: 30.9 (#284), Gemma 3 12B: 40.0 (#162)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| LMArena Longer Query | 1013 | 1317 |
Writing & Preference Gemma 3 12B leads
Codellama 34b Instruct: 28.2 (#297), Gemma 3 12B: 47.5 (#209)
| Benchmark | Codellama 34b Instruct | Gemma 3 12B |
|---|---|---|
| LMArena Text | 1066 | 1334 |
| LMArena Creative Writing | 1032 | 1331 |
| LMArena Multi-Turn | 1015 | 1334 |
| EQ-Bench Creative Writing | — | 1126 |
Frequently asked questions
Is Codellama 34b Instruct better than Gemma 3 12B?
Gemma 3 12B is the stronger model overall, scoring 32.1 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Gemma 3 12B better for coding?
Gemma 3 12B scores higher on coding benchmarks: 31.7 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Gemma 3 12B share?
9 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Gemma 3 12B has 24.