Model comparison
Llama 3.2 3B vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 28.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. Llama 3.2 3B scores higher in 1 category and Qwen1.5-32B in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.2 3B leads 29.1 to 13.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 28.3% for Llama 3.2 3B and 42% for Qwen1.5-32B.
Side by side
| Llama 3.2 3B | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.4 | 30.0 |
| Released | 2024-09-24 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Llama 3.2 3B: 27.1 (#314), Qwen1.5-32B: 31.1 (#278)
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 23.4% | 32.3% |
| LMArena Coding | 1098 | 1155 |
| BigCodeBench Complete | 28.3% | 42% |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 19.9 (#135), Qwen1.5-32B: —
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Too close to call
Llama 3.2 3B: 20.1 (#225), Qwen1.5-32B: 20.9 (#210)
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1131 |
Math Too close to call
Llama 3.2 3B: 29.9 (#213), Qwen1.5-32B: 30.5 (#207)
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1126 | 1155 |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.1 (#232), Qwen1.5-32B: 13.5 (#291)
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| LMArena Expert | 1090 | 1126 |
| GPQA Diamond | — | 30.7% |
| MMLU | — | 74.4% |
Multilingual Qwen1.5-32B leads
Llama 3.2 3B: 26.4 (#276), Qwen1.5-32B: 31.6 (#254)
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1019 | 1106 |
| LMArena Chinese | 1017 | 1176 |
| LMArena German | 1056 | 1058 |
| LMArena Russian | 949 | 1073 |
| LMArena French | — | 1100 |
| LMArena Japanese | — | 1027 |
| LMArena Korean | — | 1007 |
| LMArena Spanish | — | 1089 |
Instruction Following Qwen1.5-32B leads
Llama 3.2 3B: 56.3 (#270), Qwen1.5-32B: 58.0 (#260)
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1089 | 1116 |
Long Context Qwen1.5-32B leads
Llama 3.2 3B: 33.4 (#256), Qwen1.5-32B: 34.7 (#241)
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1101 | 1146 |
Writing & Preference Qwen1.5-32B leads
Llama 3.2 3B: 24.9 (#302), Qwen1.5-32B: 34.4 (#266)
| Benchmark | Llama 3.2 3B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1110 | 1137 |
| LMArena Creative Writing | 1094 | 1083 |
| LMArena Multi-Turn | 1105 | 1140 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 28.4 on the Noometry Index.
Is Llama 3.2 3B or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.1 versus 27.1 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Qwen1.5-32B share?
15 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Qwen1.5-32B has 21.