Model comparison
Codellama 34b Instruct vs Gemma 3 27B
Codellama 34b Instruct and Gemma 3 27B score almost the same on the Noometry Index (30.8 vs 30.8), so choose on price, context window or the category you care about most.
Last verified . 10 shared benchmarks.
Meta
GoogleSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 4 categories and Gemma 3 27B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Gemma 3 27B leads 52.5 to 28.2.
Side by side
| Codellama 34b Instruct | Gemma 3 27B | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 30.8 | 30.8 |
| Released | — | 2025-03-11 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.16 |
| Results tracked | 14 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 34b Instruct leads
Codellama 34b Instruct: 28.5 (#314), Gemma 3 27B: 22.5 (#334)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| LMArena Coding | 1046 | 1322 |
| Aider Polyglot | — | 4.9% |
| SciCode | — | 21.2% |
| BigCodeBench Instruct | 29% | — |
| LiveBench Coding | — | 39.9% |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Gemma 3 27B: 25.1 (#110)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 29.5% |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), Gemma 3 27B: 16.7 (#301)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1340 |
| 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 Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), Gemma 3 27B: 25.9 (#265)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| LMArena Math | 1056 | 1312 |
| OTIS Mock AIME 2024-2025 | — | 22.5% |
| LiveBench Math | — | 55.4% |
| MATH Level 5 | — | 74% |
Knowledge Not comparable
Codellama 34b Instruct: —, Gemma 3 27B: 25.5 (#261)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| GPQA Diamond | — | 47.7% |
| Confabulations | — | 40.3% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1304 |
Multimodal Not comparable
Codellama 34b Instruct: —, Gemma 3 27B: 32.6 (#100)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| LMArena Vision | — | 1164 |
| GeoBench | — | 52% |
Multilingual Gemma 3 27B leads
Codellama 34b Instruct: 25.8 (#284), Gemma 3 27B: 46.9 (#155)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| LMArena Non-English | 1011 | 1334 |
| LMArena Chinese | 976 | 1346 |
| LMArena French | — | 1368 |
| LMArena German | — | 1362 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1308 |
| LMArena Russian | — | 1349 |
| LMArena Spanish | — | 1349 |
Instruction Following Gemma 3 27B leads
Codellama 34b Instruct: 52.2 (#291), Gemma 3 27B: 70.6 (#160)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1321 |
| LiveBench Instruction Following | — | 74.9% |
Long Context Codellama 34b Instruct leads
Codellama 34b Instruct: 30.9 (#284), Gemma 3 27B: 27.6 (#293)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| LMArena Longer Query | 1013 | 1333 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Gemma 3 27B leads
Codellama 34b Instruct: 28.2 (#297), Gemma 3 27B: 52.5 (#168)
| Benchmark | Codellama 34b Instruct | Gemma 3 27B |
|---|---|---|
| LMArena Text | 1066 | 1358 |
| LMArena Creative Writing | 1032 | 1346 |
| LMArena Multi-Turn | 1015 | 1345 |
| Short-Story Creative Writing | — | 79.9% |
| EQ-Bench Creative Writing | — | 1266 |
| LiveBench Language | — | 34.6% |
Frequently asked questions
Is Codellama 34b Instruct better than Gemma 3 27B?
Codellama 34b Instruct and Gemma 3 27B score almost the same on the Noometry Index (30.8 vs 30.8), so choose on price, context window or the category you care about most.
Is Codellama 34b Instruct or Gemma 3 27B better for coding?
Codellama 34b Instruct scores higher on coding benchmarks: 28.5 versus 22.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Gemma 3 27B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Gemma 3 27B has 43.