Model comparison
Codellama 70b Instruct vs Qwen1.5-110B
Codellama 70b Instruct and Qwen1.5-110B score almost the same on the Noometry Index (33.7 vs 34.2), so choose on price, context window or the category you care about most.
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 Qwen1.5-110B in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-110B leads 33.6 to 24.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 40.7% for Codellama 70b Instruct and 35% for Qwen1.5-110B.
Side by side
| Codellama 70b Instruct | Qwen1.5-110B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 33.7 | 34.2 |
| Released | — | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 20 |
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), Qwen1.5-110B: 33.0 (#264)
| Benchmark | Codellama 70b Instruct | Qwen1.5-110B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 35% |
| BigCodeBench Complete | 49.6% | 44.4% |
| LMArena Coding | — | 1184 |
| HumanEval+ | 65.9% | — |
Reasoning Qwen1.5-110B leads
Codellama 70b Instruct: 20.1 (#242), Qwen1.5-110B: 22.7 (#189)
| Benchmark | Codellama 70b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1168 |
| ForecastBench | — | 57.7 |
Math Not comparable
Codellama 70b Instruct: —, Qwen1.5-110B: 33.7 (#201)
| Benchmark | Codellama 70b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Math | — | 1185 |
Knowledge Not comparable
Codellama 70b Instruct: —, Qwen1.5-110B: 31.2 (#219)
| Benchmark | Codellama 70b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | — | 1144 |
Multilingual Qwen1.5-110B leads
Codellama 70b Instruct: 24.8 (#288), Qwen1.5-110B: 33.6 (#250)
| Benchmark | Codellama 70b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 992 | 1142 |
| LMArena Chinese | — | 1206 |
| LMArena French | — | 1151 |
| LMArena German | — | 1123 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
| LMArena Russian | — | 1118 |
| LMArena Spanish | — | 1142 |
Instruction Following Qwen1.5-110B leads
Codellama 70b Instruct: 51.9 (#293), Qwen1.5-110B: 60.3 (#252)
| Benchmark | Codellama 70b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1158 |
Long Context Not comparable
Codellama 70b Instruct: —, Qwen1.5-110B: 35.1 (#242)
| Benchmark | Codellama 70b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | — | 1157 |
Writing & Preference Qwen1.5-110B leads
Codellama 70b Instruct: 33.4 (#277), Qwen1.5-110B: 38.0 (#255)
| Benchmark | Codellama 70b Instruct | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1057 | 1175 |
| LMArena Creative Writing | — | 1148 |
| LMArena Multi-Turn | — | 1160 |
Frequently asked questions
Is Codellama 70b Instruct better than Qwen1.5-110B?
Codellama 70b Instruct and Qwen1.5-110B score almost the same on the Noometry Index (33.7 vs 34.2), so choose on price, context window or the category you care about most.
Is Codellama 70b Instruct or Qwen1.5-110B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 33.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Qwen1.5-110B share?
6 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Qwen1.5-110B has 20.