Model comparison
Llama 3-8B vs Qwen1.5-32B
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 25.5 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Llama 3-8B scores higher in 2 categories and Qwen1.5-32B in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 33.0 to 8.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 36.9% for Llama 3-8B and 42% for Qwen1.5-32B.
Side by side
| Llama 3-8B | Qwen1.5-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 25.5 | 30.5 |
| Released | 2024-04-18 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-8B: 31.0 (#289), Qwen1.5-32B: 31.7 (#282)
| Benchmark | Llama 3-8B | Qwen1.5-32B |
|---|---|---|
| BigCodeBench Instruct | 31.9% | 32.3% |
| LMArena Coding | 1152 | 1155 |
| BigCodeBench Complete | 36.9% | 42% |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Qwen1.5-32B leads
Llama 3-8B: 14.3 (#326), Qwen1.5-32B: 21.8 (#212)
| Benchmark | Llama 3-8B | Qwen1.5-32B |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1130 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Qwen1.5-32B leads
Llama 3-8B: 8.8 (#323), Qwen1.5-32B: 33.0 (#207)
| Benchmark | Llama 3-8B | Qwen1.5-32B |
|---|---|---|
| LMArena Math | 1151 | 1155 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Qwen1.5-32B leads
Llama 3-8B: 7.8 (#308), Qwen1.5-32B: 13.5 (#296)
| Benchmark | Llama 3-8B | Qwen1.5-32B |
|---|---|---|
| GPQA Diamond | 26.1% | 30.7% |
| LMArena Expert | 1113 | 1126 |
| MMLU | 68.8% | 74.4% |
| ARC (AI2) Challenge | 82.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Too close to call
Llama 3-8B: 30.8 (#261), Qwen1.5-32B: 31.4 (#259)
| Benchmark | Llama 3-8B | Qwen1.5-32B |
|---|---|---|
| LMArena Non-English | 1098 | 1106 |
| LMArena Chinese | 1076 | 1177 |
| LMArena French | 1159 | 1101 |
| LMArena German | 1104 | 1058 |
| LMArena Japanese | 967 | 1027 |
| LMArena Korean | 1004 | 1008 |
| LMArena Russian | 1109 | 1073 |
| LMArena Spanish | 1173 | 1089 |
Instruction Following Too close to call
Llama 3-8B: 58.4 (#260), Qwen1.5-32B: 57.7 (#265)
| Benchmark | Llama 3-8B | Qwen1.5-32B |
|---|---|---|
| LMArena Instruction Following | 1127 | 1116 |
Long Context Too close to call
Llama 3-8B: 34.2 (#251), Qwen1.5-32B: 34.7 (#246)
| Benchmark | Llama 3-8B | Qwen1.5-32B |
|---|---|---|
| LMArena Longer Query | 1128 | 1146 |
Writing & Preference Llama 3-8B leads
Llama 3-8B: 37.5 (#256), Qwen1.5-32B: 34.2 (#271)
| Benchmark | Llama 3-8B | Qwen1.5-32B |
|---|---|---|
| LMArena Text | 1166 | 1137 |
| LMArena Creative Writing | 1150 | 1083 |
| LMArena Multi-Turn | 1152 | 1140 |
Frequently asked questions
Is Llama 3-8B better than Qwen1.5-32B?
Qwen1.5-32B is the stronger model overall, scoring 30.5 to 25.5 on the Noometry Index.
Is Llama 3-8B or Qwen1.5-32B better for coding?
They score almost the same on coding (31.0 vs 31.7); test both on your own repository before choosing.
How many benchmarks do Llama 3-8B and Qwen1.5-32B share?
21 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Qwen1.5-32B has 21.