Model comparison
Codellama 34b Instruct vs Qwen2-72B
Codellama 34b Instruct and Qwen2-72B score almost the same on the Noometry Index (30.8 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Codellama 34b Instruct scores higher in 1 category and Qwen2-72B in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2-72B leads 40.8 to 28.2.
- The biggest single-benchmark swing is BigCodeBench Complete: 37.1% for Codellama 34b Instruct and 54% for Qwen2-72B.
Side by side
| Codellama 34b Instruct | Qwen2-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.8 | 30.0 |
| Released | — | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 34b Instruct: 28.5 (#314), Qwen2-72B: 29.1 (#310)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 29% | 38.5% |
| LMArena Coding | 1046 | 1196 |
| BigCodeBench Complete | 37.1% | 54% |
| WeirdML | — | 11.3% |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Codellama 34b Instruct: 19.6 (#255), Qwen2-72B: 23.2 (#181)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Too close to call
Codellama 34b Instruct: 31.0 (#230), Qwen2-72B: 30.2 (#236)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Math | 1056 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Not comparable
Codellama 34b Instruct: —, Qwen2-72B: 21.2 (#275)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multilingual Qwen2-72B leads
Codellama 34b Instruct: 25.8 (#284), Qwen2-72B: 35.9 (#244)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1011 | 1176 |
| LMArena Chinese | 976 | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Qwen2-72B leads
Codellama 34b Instruct: 52.2 (#291), Qwen2-72B: 61.7 (#241)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1181 |
Long Context Qwen2-72B leads
Codellama 34b Instruct: 30.9 (#284), Qwen2-72B: 36.1 (#235)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1013 | 1192 |
Writing & Preference Qwen2-72B leads
Codellama 34b Instruct: 28.2 (#297), Qwen2-72B: 40.8 (#241)
| Benchmark | Codellama 34b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | 1066 | 1203 |
| LMArena Creative Writing | 1032 | 1181 |
| LMArena Multi-Turn | 1015 | 1196 |
Frequently asked questions
Is Codellama 34b Instruct better than Qwen2-72B?
Codellama 34b Instruct and Qwen2-72B score almost the same on the Noometry Index (30.8 vs 30.0), so choose on price, context window or the category you care about most.
Is Codellama 34b Instruct or Qwen2-72B better for coding?
They score almost the same on coding (28.5 vs 29.1); test both on your own repository before choosing.
How many benchmarks do Codellama 34b Instruct and Qwen2-72B share?
12 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Qwen2-72B has 26.