Model comparison
Llama 3.2 3B vs Qwen1.5-72B
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 28.9 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 Qwen1.5-72B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Llama 3.2 3B leads 29.7 to 11.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 28.3% for Llama 3.2 3B and 40.3% for Qwen1.5-72B.
Side by side
| Llama 3.2 3B | Qwen1.5-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.9 | 30.8 |
| 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 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-72B leads
Llama 3.2 3B: 27.6 (#319), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 23.4% | 33.2% |
| LMArena Coding | 1098 | 1165 |
| BigCodeBench Complete | 28.3% | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Qwen1.5-72B: —
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Qwen1.5-72B leads
Llama 3.2 3B: 21.0 (#228), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1148 |
Math Too close to call
Llama 3.2 3B: 32.4 (#214), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1126 | 1164 |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.7 (#235), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1090 | 1136 |
| GPQA Diamond | — | 28.8% |
Multilingual Qwen1.5-72B leads
Llama 3.2 3B: 26.2 (#281), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1019 | 1135 |
| LMArena Chinese | 1017 | 1186 |
| LMArena German | 1056 | 1084 |
| LMArena Russian | 949 | 1104 |
| LMArena French | — | 1159 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1050 |
| LMArena Spanish | — | 1110 |
Instruction Following Qwen1.5-72B leads
Llama 3.2 3B: 56.0 (#275), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1089 | 1141 |
Long Context Qwen1.5-72B leads
Llama 3.2 3B: 33.4 (#261), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1100 | 1157 |
Writing & Preference Qwen1.5-72B leads
Llama 3.2 3B: 24.7 (#307), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Llama 3.2 3B | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1110 | 1166 |
| LMArena Creative Writing | 1094 | 1137 |
| LMArena Multi-Turn | 1105 | 1160 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Qwen1.5-72B?
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 28.9 on the Noometry Index.
Is Llama 3.2 3B or Qwen1.5-72B better for coding?
Qwen1.5-72B scores higher on coding benchmarks: 31.9 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Qwen1.5-72B share?
15 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Qwen1.5-72B has 22.