Model comparison
Codellama 70b Instruct vs Qwen2-72B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.0 on the Noometry Index.
Last verified . 6 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 6 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Qwen2-72B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen2-72B leads 35.9 to 24.8.
Side by side
| Codellama 70b Instruct | Qwen2-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 30.0 |
| Released | — | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 26 |
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), Qwen2-72B: 29.1 (#310)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 38.5% |
| BigCodeBench Complete | 49.6% | 54% |
| WeirdML | — | 11.3% |
| LMArena Coding | — | 1196 |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Codellama 70b Instruct: 20.1 (#242), Qwen2-72B: 23.2 (#181)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1191 |
| Epoch Capabilities Index | — | 125.28 |
Math Not comparable
Codellama 70b Instruct: —, Qwen2-72B: 30.2 (#236)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Math | — | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Not comparable
Codellama 70b Instruct: —, Qwen2-72B: 21.2 (#275)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multilingual Qwen2-72B leads
Codellama 70b Instruct: 24.8 (#288), Qwen2-72B: 35.9 (#244)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 992 | 1176 |
| LMArena Chinese | — | 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 70b Instruct: 51.9 (#293), Qwen2-72B: 61.7 (#241)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1181 |
Long Context Not comparable
Codellama 70b Instruct: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Qwen2-72B leads
Codellama 70b Instruct: 33.4 (#277), Qwen2-72B: 40.8 (#241)
| Benchmark | Codellama 70b Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | 1057 | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Codellama 70b Instruct better than Qwen2-72B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.0 on the Noometry Index.
Is Codellama 70b Instruct or Qwen2-72B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 29.1 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Qwen2-72B share?
6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen2-72B has 26.