Model comparison
Llama 3.2 3B vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 30.8 to 28.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Llama 3.2 3B scores higher in 4 categories and Qwen-14B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3.2 3B leads 56.3 to 52.6.
Side by side
| Llama 3.2 3B | Qwen-14B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.4 | 30.8 |
| Released | 2024-09-24 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen-14B leads
Llama 3.2 3B: 27.1 (#314), Qwen-14B: 30.6 (#283)
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| LMArena Coding | 1098 | 1072 |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 19.9 (#135), Qwen-14B: —
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Llama 3.2 3B leads
Llama 3.2 3B: 20.1 (#225), Qwen-14B: 18.7 (#255)
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1027 |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 112.8 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Llama 3.2 3B leads
Llama 3.2 3B: 29.9 (#213), Qwen-14B: 28.7 (#224)
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| LMArena Math | 1126 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Llama 3.2 3B: 29.1 (#232), Qwen-14B: —
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| LMArena Expert | 1090 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Qwen-14B leads
Llama 3.2 3B: 26.4 (#276), Qwen-14B: 27.7 (#270)
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1019 | 1042 |
| LMArena Chinese | 1017 | 1077 |
| LMArena German | 1056 | — |
| LMArena Russian | 949 | — |
Instruction Following Llama 3.2 3B leads
Llama 3.2 3B: 56.3 (#270), Qwen-14B: 52.6 (#284)
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1089 | 1031 |
Long Context Llama 3.2 3B leads
Llama 3.2 3B: 33.4 (#256), Qwen-14B: 31.3 (#276)
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1101 | 1029 |
Writing & Preference Qwen-14B leads
Llama 3.2 3B: 24.9 (#302), Qwen-14B: 27.8 (#294)
| Benchmark | Llama 3.2 3B | Qwen-14B |
|---|---|---|
| LMArena Text | 1110 | 1051 |
| LMArena Creative Writing | 1094 | 1028 |
| LMArena Multi-Turn | 1105 | 1022 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 30.8 to 28.4 on the Noometry Index.
Is Llama 3.2 3B or Qwen-14B better for coding?
Qwen-14B scores higher on coding benchmarks: 30.6 versus 27.1 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Qwen-14B share?
10 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Qwen-14B has 18.