Model comparison
Llama 13b vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 23.9 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Qwen1.5-32B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Qwen1.5-32B leads 58.0 to 36.9.
Side by side
| Llama 13b | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.9 | 30.0 |
| Released | 2023-02-24 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Llama 13b: 20.9 (#332), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 683 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Qwen1.5-32B leads
Llama 13b: 13.4 (#327), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1131 |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.09 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Qwen1.5-32B leads
Llama 13b: 24.4 (#259), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 838 | 1155 |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Qwen1.5-32B: 13.5 (#291)
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| MMLU | 47.7% | 74.4% |
| GPQA Diamond | — | 30.7% |
| LMArena Expert | — | 1126 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Qwen1.5-32B: —
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Qwen1.5-32B leads
Llama 13b: 16.8 (#292), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 819 | 1106 |
| LMArena Chinese | — | 1176 |
| LMArena French | — | 1100 |
| LMArena German | — | 1058 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1007 |
| LMArena Russian | — | 1073 |
| LMArena Spanish | — | 1089 |
Instruction Following Qwen1.5-32B leads
Llama 13b: 36.9 (#300), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 781 | 1116 |
Long Context Not comparable
Llama 13b: —, Qwen1.5-32B: 34.7 (#241)
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | — | 1146 |
Writing & Preference Qwen1.5-32B leads
Llama 13b: 13.9 (#307), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Llama 13b | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 834 | 1137 |
| LMArena Creative Writing | 794 | 1083 |
| LMArena Multi-Turn | 753 | 1140 |
Frequently asked questions
Is Llama 13b better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 23.9 on the Noometry Index.
Is Llama 13b or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.1 versus 20.9 in the Noometry coding category.
How many benchmarks do Llama 13b and Qwen1.5-32B share?
9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Qwen1.5-32B has 21.