Model comparison
Codellama 34b Instruct vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and Qwen3 32B in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 52.9 to 28.2.
Side by side
| Codellama 34b Instruct | Qwen3 32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.8 | 39.2 |
| Released | — | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 14 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Codellama 34b Instruct: 28.5 (#314), Qwen3 32B: 37.7 (#190)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1046 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Too close to call
Codellama 34b Instruct: 19.6 (#255), Qwen3 32B: 20.2 (#241)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1334 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Qwen3 32B leads
Codellama 34b Instruct: 31.0 (#230), Qwen3 32B: 39.7 (#99)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Math | 1056 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
Knowledge Not comparable
Codellama 34b Instruct: —, Qwen3 32B: 40.0 (#125)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
Multilingual Qwen3 32B leads
Codellama 34b Instruct: 25.8 (#284), Qwen3 32B: 45.6 (#167)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1011 | 1317 |
| LMArena Chinese | 976 | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Qwen3 32B leads
Codellama 34b Instruct: 52.2 (#291), Qwen3 32B: 68.9 (#179)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1305 |
Long Context Qwen3 32B leads
Codellama 34b Instruct: 30.9 (#284), Qwen3 32B: 43.8 (#87)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1013 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Codellama 34b Instruct: 28.2 (#297), Qwen3 32B: 52.9 (#163)
| Benchmark | Codellama 34b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Text | 1066 | 1340 |
| LMArena Creative Writing | 1032 | 1297 |
| LMArena Multi-Turn | 1015 | 1331 |
Frequently asked questions
Is Codellama 34b Instruct better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Qwen3 32B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Qwen3 32B has 26.