Model comparison
Llama 3.1-70B vs Qwen1.5-32B
Llama 3.1-70B and Qwen1.5-32B score almost the same on the Noometry Index (29.6 vs 30.5), so choose on price, context window or the category you care about most.
Last verified . 21 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Llama 3.1-70B scores higher in 5 categories and Qwen1.5-32B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 33.0 to 13.5.
- The biggest single-benchmark swing is BigCodeBench Instruct: 46.1% for Llama 3.1-70B and 32.3% for Qwen1.5-32B.
Side by side
| Llama 3.1-70B | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 30.5 |
| Released | 2024-07-23 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-32B leads
Llama 3.1-70B: 30.3 (#296), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 46.1% | 32.3% |
| LMArena Coding | 1260 | 1155 |
| BigCodeBench Complete | 54.8% | 42% |
| WeirdML | 9% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 25.1 (#112), Qwen1.5-32B: —
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Too close to call
Llama 3.1-70B: 21.6 (#220), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1130 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.92 | — |
Math Qwen1.5-32B leads
Llama 3.1-70B: 13.5 (#304), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1252 | 1155 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
Knowledge Llama 3.1-70B leads
Llama 3.1-70B: 24.2 (#269), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 44.2% | 30.7% |
| LMArena Expert | 1209 | 1126 |
| MMLU | 80.1% | 74.4% |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
Multilingual Llama 3.1-70B leads
Llama 3.1-70B: 38.8 (#225), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1219 | 1106 |
| LMArena Chinese | 1215 | 1177 |
| LMArena French | 1261 | 1101 |
| LMArena German | 1222 | 1058 |
| LMArena Japanese | 1132 | 1027 |
| LMArena Korean | 1140 | 1008 |
| LMArena Russian | 1234 | 1073 |
| LMArena Spanish | 1253 | 1089 |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.3 (#223), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1231 | 1116 |
| IFEval | 82.1% | — |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#214), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1241 | 1146 |
Writing & Preference Llama 3.1-70B leads
Llama 3.1-70B: 35.4 (#267), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Llama 3.1-70B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1261 | 1137 |
| LMArena Creative Writing | 1232 | 1083 |
| LMArena Multi-Turn | 1256 | 1140 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Qwen1.5-32B?
Llama 3.1-70B and Qwen1.5-32B score almost the same on the Noometry Index (29.6 vs 30.5), so choose on price, context window or the category you care about most.
Is Llama 3.1-70B or Qwen1.5-32B better for coding?
Qwen1.5-32B scores higher on coding benchmarks: 31.7 versus 30.3 in the Noometry coding category.
How many benchmarks do Llama 3.1-70B and Qwen1.5-32B share?
21 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Qwen1.5-32B has 21.