Model comparison
Codellama 70b Instruct vs Qwen1.5-14B
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 32.1 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 1 category and Qwen1.5-14B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-14B leads 30.8 to 24.9.
Side by side
| Codellama 70b Instruct | Qwen1.5-14B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.3 | 32.1 |
| Released | — | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.0 (#189), Qwen1.5-14B: 32.5 (#259)
| Benchmark | Codellama 70b Instruct | Qwen1.5-14B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1138 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Qwen1.5-14B leads
Codellama 70b Instruct: 19.2 (#241), Qwen1.5-14B: 20.5 (#217)
| Benchmark | Codellama 70b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1113 |
Math Not comparable
Codellama 70b Instruct: —, Qwen1.5-14B: 29.9 (#214)
| Benchmark | Codellama 70b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Math | — | 1125 |
Knowledge Not comparable
Codellama 70b Instruct: —, Qwen1.5-14B: 29.3 (#230)
| Benchmark | Codellama 70b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Expert | — | 1094 |
| MMLU | — | 68.6% |
Multilingual Qwen1.5-14B leads
Codellama 70b Instruct: 24.9 (#283), Qwen1.5-14B: 30.8 (#257)
| Benchmark | Codellama 70b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Non-English | 992 | 1095 |
| LMArena Chinese | — | 1147 |
| LMArena French | — | 1115 |
| LMArena German | — | 1043 |
| LMArena Japanese | — | 1019 |
| LMArena Russian | — | 1046 |
| LMArena Spanish | — | 1085 |
Instruction Following Qwen1.5-14B leads
Codellama 70b Instruct: 52.1 (#288), Qwen1.5-14B: 57.1 (#266)
| Benchmark | Codellama 70b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1102 |
Long Context Not comparable
Codellama 70b Instruct: —, Qwen1.5-14B: 33.7 (#252)
| Benchmark | Codellama 70b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Longer Query | — | 1113 |
Writing & Preference Too close to call
Codellama 70b Instruct: 33.6 (#272), Qwen1.5-14B: 33.7 (#270)
| Benchmark | Codellama 70b Instruct | Qwen1.5-14B |
|---|---|---|
| LMArena Text | 1057 | 1128 |
| LMArena Creative Writing | — | 1091 |
| LMArena Multi-Turn | — | 1110 |
Frequently asked questions
Is Codellama 70b Instruct better than Qwen1.5-14B?
Codellama 70b Instruct is the stronger model overall, scoring 33.3 to 32.1 on the Noometry Index.
Is Codellama 70b Instruct or Qwen1.5-14B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 32.5 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Qwen1.5-14B share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen1.5-14B has 17.