Model comparison
Codellama 70b Instruct vs Qwen1.5-32B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.5 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 Qwen1.5-32B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-32B leads 31.4 to 24.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 40.7% for Codellama 70b Instruct and 32.3% for Qwen1.5-32B.
Side by side
| Codellama 70b Instruct | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 30.5 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 21 |
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), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Codellama 70b Instruct | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 32.3% |
| BigCodeBench Complete | 49.6% | 42% |
| LMArena Coding | — | 1155 |
| HumanEval+ | 65.9% | — |
Reasoning Qwen1.5-32B leads
Codellama 70b Instruct: 20.1 (#242), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Codellama 70b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1130 |
Math Not comparable
Codellama 70b Instruct: —, Qwen1.5-32B: 33.0 (#207)
| Benchmark | Codellama 70b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Math | — | 1155 |
Knowledge Not comparable
Codellama 70b Instruct: —, Qwen1.5-32B: 13.5 (#296)
| Benchmark | Codellama 70b Instruct | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | — | 30.7% |
| LMArena Expert | — | 1126 |
| MMLU | — | 74.4% |
Multilingual Qwen1.5-32B leads
Codellama 70b Instruct: 24.8 (#288), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Codellama 70b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 992 | 1106 |
| LMArena Chinese | — | 1177 |
| LMArena French | — | 1101 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1008 |
| LMArena Russian | — | 1073 |
| LMArena Spanish | — | 1089 |
Instruction Following Qwen1.5-32B leads
Codellama 70b Instruct: 51.9 (#293), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Codellama 70b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1116 |
Long Context Not comparable
Codellama 70b Instruct: —, Qwen1.5-32B: 34.7 (#246)
| Benchmark | Codellama 70b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | — | 1146 |
Writing & Preference Too close to call
Codellama 70b Instruct: 33.4 (#277), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Codellama 70b Instruct | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1057 | 1137 |
| LMArena Creative Writing | — | 1083 |
| LMArena Multi-Turn | — | 1140 |
Frequently asked questions
Is Codellama 70b Instruct better than Qwen1.5-32B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 30.5 on the Noometry Index.
Is Codellama 70b Instruct or Qwen1.5-32B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 31.7 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Qwen1.5-32B share?
6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen1.5-32B has 21.