Model comparison
Llama 2-13B vs Qwen1.5-72B
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 29.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Llama 2-13B 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 2-13B leads 28.1 to 11.5.
Side by side
| Llama 2-13B | Qwen1.5-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 30.8 |
| Released | 2023-07-18 | 2024-02-04 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 2-13B: 30.9 (#291), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1062 | 1165 |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Reasoning Qwen1.5-72B leads
Llama 2-13B: 12.8 (#337), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1148 |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 106.17 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Qwen1.5-72B leads
Llama 2-13B: 31.1 (#229), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1065 | 1164 |
| GSM8K | 36.9% | — |
Knowledge Llama 2-13B leads
Llama 2-13B: 28.1 (#249), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1030 | 1136 |
| GPQA Diamond | — | 28.8% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Qwen1.5-72B: —
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Qwen1.5-72B leads
Llama 2-13B: 26.5 (#279), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1024 | 1135 |
| LMArena Chinese | 1001 | 1186 |
| LMArena French | 1044 | 1159 |
| LMArena German | 1009 | 1084 |
| LMArena Japanese | 894 | 1061 |
| LMArena Korean | 953 | 1050 |
| LMArena Russian | 1055 | 1104 |
| LMArena Spanish | 1087 | 1110 |
Instruction Following Qwen1.5-72B leads
Llama 2-13B: 53.3 (#287), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1045 | 1141 |
Long Context Qwen1.5-72B leads
Llama 2-13B: 32.3 (#269), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1064 | 1157 |
Writing & Preference Qwen1.5-72B leads
Llama 2-13B: 29.8 (#289), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Llama 2-13B | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1084 | 1166 |
| LMArena Creative Writing | 1047 | 1137 |
| LMArena Multi-Turn | 1050 | 1160 |
Frequently asked questions
Is Llama 2-13B better than Qwen1.5-72B?
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 29.6 on the Noometry Index.
Is Llama 2-13B or Qwen1.5-72B better for coding?
They score almost the same on coding (30.9 vs 31.9); test both on your own repository before choosing.
How many benchmarks do Llama 2-13B and Qwen1.5-72B share?
17 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Qwen1.5-72B has 22.