Model comparison
Llama 2-13B vs Qwen1.5-32B
Llama 2-13B and Qwen1.5-32B score almost the same on the Noometry Index (29.1 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Llama 2-13B scores higher in 1 category and Qwen1.5-32B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 2-13B leads 27.5 to 13.5.
Side by side
| Llama 2-13B | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.1 | 30.0 |
| Released | 2023-07-18 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 2-13B: 30.4 (#287), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| LMArena Coding | 1062 | 1155 |
| BigCodeBench Instruct | — | 32.3% |
| BigCodeBench Complete | — | 42% |
Reasoning Qwen1.5-32B leads
Llama 2-13B: 12.3 (#333), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1131 |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 105.8 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Qwen1.5-32B leads
Llama 2-13B: 28.7 (#226), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1065 | 1155 |
| GSM8K | 36.9% | — |
Knowledge Llama 2-13B leads
Llama 2-13B: 27.5 (#244), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1030 | 1126 |
| MMLU | 55.6% | 74.4% |
| GPQA Diamond | — | 30.7% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Qwen1.5-32B: —
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Qwen1.5-32B leads
Llama 2-13B: 26.7 (#274), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1024 | 1106 |
| LMArena Chinese | 1001 | 1176 |
| LMArena French | 1043 | 1100 |
| LMArena German | 1009 | 1058 |
| LMArena Japanese | 894 | 1027 |
| LMArena Korean | 953 | 1007 |
| LMArena Russian | 1055 | 1073 |
| LMArena Spanish | 1086 | 1089 |
Instruction Following Qwen1.5-32B leads
Llama 2-13B: 53.5 (#282), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1046 | 1116 |
Long Context Qwen1.5-32B leads
Llama 2-13B: 32.3 (#264), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1064 | 1146 |
Writing & Preference Qwen1.5-32B leads
Llama 2-13B: 30.0 (#284), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Llama 2-13B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1085 | 1137 |
| LMArena Creative Writing | 1047 | 1083 |
| LMArena Multi-Turn | 1050 | 1140 |
Frequently asked questions
Is Llama 2-13B better than Qwen1.5-32B?
Llama 2-13B and Qwen1.5-32B score almost the same on the Noometry Index (29.1 vs 30.0), so choose on price, context window or the category you care about most.
Is Llama 2-13B or Qwen1.5-32B better for coding?
They score almost the same on coding (30.4 vs 31.1); test both on your own repository before choosing.
How many benchmarks do Llama 2-13B and Qwen1.5-32B share?
18 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Qwen1.5-32B has 21.