Model comparison
Codellama 70b Instruct vs Qwen1.5-7B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 31.4 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 2 categories and Qwen1.5-7B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 32.2.
Side by side
| Codellama 70b Instruct | Qwen1.5-7B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 31.4 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 13 |
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), Qwen1.5-7B: 32.2 (#276)
| Benchmark | Codellama 70b Instruct | Qwen1.5-7B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1107 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Too close to call
Codellama 70b Instruct: 20.1 (#242), Qwen1.5-7B: 20.4 (#240)
| Benchmark | Codellama 70b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1065 |
Math Not comparable
Codellama 70b Instruct: —, Qwen1.5-7B: 31.4 (#224)
| Benchmark | Codellama 70b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Math | — | 1080 |
Knowledge Not comparable
Codellama 70b Instruct: —, Qwen1.5-7B: 28.7 (#243)
| Benchmark | Codellama 70b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | — | 1055 |
| MMLU | — | 62.6% |
Multilingual Qwen1.5-7B leads
Codellama 70b Instruct: 24.8 (#288), Qwen1.5-7B: 28.5 (#271)
| Benchmark | Codellama 70b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 992 | 1058 |
| LMArena Chinese | — | 1141 |
| LMArena Russian | — | 1006 |
Instruction Following Qwen1.5-7B leads
Codellama 70b Instruct: 51.9 (#293), Qwen1.5-7B: 54.1 (#281)
| Benchmark | Codellama 70b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1058 |
Long Context Not comparable
Codellama 70b Instruct: —, Qwen1.5-7B: 33.1 (#266)
| Benchmark | Codellama 70b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | — | 1090 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.4 (#277), Qwen1.5-7B: 29.6 (#293)
| Benchmark | Codellama 70b Instruct | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1057 | 1083 |
| LMArena Creative Writing | — | 1035 |
| LMArena Multi-Turn | — | 1062 |
Frequently asked questions
Is Codellama 70b Instruct better than Qwen1.5-7B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 31.4 on the Noometry Index.
Is Codellama 70b Instruct or Qwen1.5-7B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 32.2 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Qwen1.5-7B share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen1.5-7B has 13.