Model comparison
Codellama 70b Instruct vs Qwen2.5-Coder-32B
Codellama 70b Instruct and Qwen2.5-Coder-32B score almost the same on the Noometry Index (33.7 vs 33.4), so choose on price, context window or the category you care about most.
Last verified . 7 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Qwen2.5-Coder-32B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 22.6.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 58% for Qwen2.5-Coder-32B.
Side by side
| Codellama 70b Instruct | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 33.4 |
| Released | — | 2024-09-18 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 7 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Codellama 70b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 49% |
| BigCodeBench Complete | 49.6% | 58% |
| HumanEval+ | 65.9% | 87.2% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LiveBench Coding | — | 56.9% |
| LMArena Coding | — | 1276 |
| MBPP+ | — | 77% |
Reasoning Qwen2.5-Coder-32B leads
Codellama 70b Instruct: 20.1 (#242), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Codellama 70b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1251 |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Not comparable
Codellama 70b Instruct: —, Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Codellama 70b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | — | 46.6% |
| LMArena Math | — | 1251 |
| GSM8K | — | 93% |
Knowledge Not comparable
Codellama 70b Instruct: —, Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Codellama 70b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | — | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multilingual Qwen2.5-Coder-32B leads
Codellama 70b Instruct: 24.8 (#288), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Codellama 70b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 992 | 1205 |
| LMArena Chinese | — | 1222 |
| LMArena Russian | — | 1228 |
Instruction Following Qwen2.5-Coder-32B leads
Codellama 70b Instruct: 51.9 (#293), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Codellama 70b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Not comparable
Codellama 70b Instruct: —, Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Codellama 70b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | — | 1251 |
Writing & Preference Qwen2.5-Coder-32B leads
Codellama 70b Instruct: 33.4 (#277), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Codellama 70b Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1057 | 1230 |
| LMArena Creative Writing | — | 1174 |
| LMArena Multi-Turn | — | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Codellama 70b Instruct better than Qwen2.5-Coder-32B?
Codellama 70b Instruct and Qwen2.5-Coder-32B score almost the same on the Noometry Index (33.7 vs 33.4), so choose on price, context window or the category you care about most.
Is Codellama 70b Instruct or Qwen2.5-Coder-32B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 22.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Qwen2.5-Coder-32B share?
7 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen2.5-Coder-32B has 31.