Model comparison
Llama 2-7B vs Qwen1.5 4b Chat
Llama 2-7B and Qwen1.5 4b Chat score almost the same on the Noometry Index (28.6 vs 28.3), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Llama 2-7B scores higher in 6 categories and Qwen1.5 4b Chat in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 2-7B leads 28.1 to 23.9.
Side by side
| Llama 2-7B | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.6 | 28.3 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 2-7B: 28.7 (#302), Qwen1.5 4b Chat: 28.6 (#305)
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1002 | 999 |
Reasoning Qwen1.5 4b Chat leads
Llama 2-7B: 15.1 (#309), Qwen1.5 4b Chat: 17.7 (#277)
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1009 | 976 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 98.54 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Too close to call
Llama 2-7B: 28.2 (#231), Qwen1.5 4b Chat: 27.9 (#233)
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1042 | 1026 |
| GSM8K | 16.7% | — |
Knowledge Llama 2-7B leads
Llama 2-7B: 27.7 (#243), Qwen1.5 4b Chat: 26.2 (#252)
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1036 | 980 |
| 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 4b Chat: —
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Too close to call
Llama 2-7B: 23.9 (#288), Qwen1.5 4b Chat: 24.2 (#285)
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 973 | 979 |
| LMArena Chinese | 973 | 1024 |
| LMArena German | 978 | 902 |
| LMArena Russian | 995 | 952 |
| LMArena French | 969 | — |
| LMArena Spanish | 1007 | — |
Instruction Following Llama 2-7B leads
Llama 2-7B: 51.0 (#293), Qwen1.5 4b Chat: 49.3 (#295)
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1006 | 979 |
Long Context Too close to call
Llama 2-7B: 30.4 (#282), Qwen1.5 4b Chat: 30.1 (#285)
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 999 | 988 |
Writing & Preference Llama 2-7B leads
Llama 2-7B: 28.1 (#293), Qwen1.5 4b Chat: 23.9 (#304)
| Benchmark | Llama 2-7B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1053 | 997 |
| LMArena Creative Writing | 1033 | 969 |
| LMArena Multi-Turn | 1029 | 977 |
Frequently asked questions
Is Llama 2-7B better than Qwen1.5 4b Chat?
Llama 2-7B and Qwen1.5 4b Chat score almost the same on the Noometry Index (28.6 vs 28.3), so choose on price, context window or the category you care about most.
Is Llama 2-7B or Qwen1.5 4b Chat better for coding?
They score almost the same on coding (28.7 vs 28.6); test both on your own repository before choosing.
How many benchmarks do Llama 2-7B and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Qwen1.5 4b Chat has 13.