Model comparison
Codellama 70b Instruct vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Qwen3 32B in 5 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen3 32B leads 45.6 to 24.8.
Side by side
| Codellama 70b Instruct | Qwen3 32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 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 | 7 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 70b Instruct: 37.6 (#193), Qwen3 32B: 37.7 (#190)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1358 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Too close to call
Codellama 70b Instruct: 20.1 (#242), Qwen3 32B: 20.2 (#241)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1334 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| Epoch Capabilities Index | — | 138.51 |
Math Not comparable
Codellama 70b Instruct: —, Qwen3 32B: 39.7 (#99)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| LMArena Math | — | 1399 |
Knowledge Not comparable
Codellama 70b Instruct: —, Qwen3 32B: 40.0 (#125)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
Multilingual Qwen3 32B leads
Codellama 70b Instruct: 24.8 (#288), Qwen3 32B: 45.6 (#167)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 992 | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Qwen3 32B leads
Codellama 70b Instruct: 51.9 (#293), Qwen3 32B: 68.9 (#179)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1305 |
Long Context Not comparable
Codellama 70b Instruct: —, Qwen3 32B: 43.8 (#87)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |
Writing & Preference Qwen3 32B leads
Codellama 70b Instruct: 33.4 (#277), Qwen3 32B: 52.9 (#163)
| Benchmark | Codellama 70b Instruct | Qwen3 32B |
|---|---|---|
| LMArena Text | 1057 | 1340 |
| LMArena Creative Writing | — | 1297 |
| LMArena Multi-Turn | — | 1331 |
Frequently asked questions
Is Codellama 70b Instruct better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Qwen3 32B better for coding?
They score almost the same on coding (37.6 vs 37.7); test both on your own repository before choosing.
How many benchmarks do Codellama 70b Instruct and Qwen3 32B share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen3 32B has 26.