Model comparison
Llama 2-7B vs Qwen1.5-110B
Qwen1.5-110B is the stronger model overall, scoring 33.6 to 28.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and Qwen1.5-110B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen1.5-110B leads 38.1 to 28.1.
Side by side
| Llama 2-7B | Qwen1.5-110B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.6 | 33.6 |
| Released | 2023-07-18 | 2024-04-25 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-110B leads
Llama 2-7B: 28.7 (#302), Qwen1.5-110B: 32.4 (#260)
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1002 | 1184 |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
Reasoning Qwen1.5-110B leads
Llama 2-7B: 15.1 (#309), Qwen1.5-110B: 21.7 (#192)
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1168 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 98.54 | — |
| ForecastBench | — | 57.7 |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Qwen1.5-110B leads
Llama 2-7B: 28.2 (#231), Qwen1.5-110B: 31.1 (#199)
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1042 | 1185 |
| GSM8K | 16.7% | — |
Knowledge Qwen1.5-110B leads
Llama 2-7B: 27.7 (#243), Qwen1.5-110B: 30.7 (#217)
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1036 | 1144 |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Qwen1.5-110B: —
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Qwen1.5-110B leads
Llama 2-7B: 23.9 (#288), Qwen1.5-110B: 33.8 (#245)
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 973 | 1142 |
| LMArena Chinese | 973 | 1206 |
| LMArena French | 969 | 1150 |
| LMArena German | 978 | 1123 |
| LMArena Russian | 995 | 1118 |
| LMArena Spanish | 1007 | 1141 |
| LMArena Japanese | — | 1074 |
| LMArena Korean | — | 1044 |
Instruction Following Qwen1.5-110B leads
Llama 2-7B: 51.0 (#293), Qwen1.5-110B: 60.6 (#247)
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1006 | 1158 |
Long Context Qwen1.5-110B leads
Llama 2-7B: 30.4 (#282), Qwen1.5-110B: 35.0 (#237)
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 999 | 1157 |
Writing & Preference Qwen1.5-110B leads
Llama 2-7B: 28.1 (#293), Qwen1.5-110B: 38.1 (#250)
| Benchmark | Llama 2-7B | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1053 | 1175 |
| LMArena Creative Writing | 1033 | 1148 |
| LMArena Multi-Turn | 1029 | 1160 |
Frequently asked questions
Is Llama 2-7B better than Qwen1.5-110B?
Qwen1.5-110B is the stronger model overall, scoring 33.6 to 28.6 on the Noometry Index.
Is Llama 2-7B or Qwen1.5-110B better for coding?
Qwen1.5-110B scores higher on coding benchmarks: 32.4 versus 28.7 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Qwen1.5-110B share?
15 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Qwen1.5-110B has 20.