Model comparison
Llama 3-70B vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 28.8 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Llama 3-70B scores higher in 6 categories and Qwen1.5-32B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 33.0 to 12.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 54.5% for Llama 3-70B and 42% for Qwen1.5-32B.
Side by side
| Llama 3-70B | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.8 | 30.5 |
| Released | 2024-04-18 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 31 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 3-70B: 35.8 (#218), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 43.6% | 32.3% |
| LMArena Coding | 1206 | 1155 |
| BigCodeBench Complete | 54.5% | 42% |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Qwen1.5-32B: —
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| Cybench | 5% | — |
Reasoning Qwen1.5-32B leads
Llama 3-70B: 18.0 (#288), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1130 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Qwen1.5-32B leads
Llama 3-70B: 12.8 (#305), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1218 | 1155 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| MATH Level 5 | 22.6% | — |
Knowledge Llama 3-70B leads
Llama 3-70B: 20.8 (#277), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 40.6% | 30.7% |
| LMArena Expert | 1149 | 1126 |
| MMLU | 79.3% | 74.4% |
Multilingual Llama 3-70B leads
Llama 3-70B: 33.6 (#251), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1142 | 1106 |
| LMArena Chinese | 1114 | 1177 |
| LMArena French | 1232 | 1101 |
| LMArena German | 1169 | 1058 |
| LMArena Japanese | 1017 | 1027 |
| LMArena Korean | 1017 | 1008 |
| LMArena Russian | 1159 | 1073 |
| LMArena Spanish | 1241 | 1089 |
Instruction Following Llama 3-70B leads
Llama 3-70B: 62.5 (#238), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1194 | 1116 |
Long Context Too close to call
Llama 3-70B: 35.6 (#240), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1174 | 1146 |
Writing & Preference Llama 3-70B leads
Llama 3-70B: 42.8 (#231), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Llama 3-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1221 | 1137 |
| LMArena Creative Writing | 1210 | 1083 |
| LMArena Multi-Turn | 1223 | 1140 |
Frequently asked questions
Is Llama 3-70B better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 28.8 on the Noometry Index.
Is Llama 3-70B or Qwen1.5-32B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 31.7 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Qwen1.5-32B share?
21 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Qwen1.5-32B has 21.