Model comparison
Llama 2-70B vs Qwen1.5 4b Chat
Qwen1.5 4b Chat is the stronger model overall, scoring 28.8 to 24.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Llama 2-70B scores higher in 5 categories and Qwen1.5 4b Chat in 3 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5 4b Chat leads 30.4 to 8.1.
Side by side
| Llama 2-70B | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 24.4 | 28.8 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-70B leads
Llama 2-70B: 31.4 (#286), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Llama 2-70B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1079 | 999 |
Reasoning Qwen1.5 4b Chat leads
Llama 2-70B: 14.4 (#325), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Llama 2-70B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1073 | 976 |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Qwen1.5 4b Chat leads
Llama 2-70B: 8.1 (#326), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Llama 2-70B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1091 | 1026 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Qwen1.5 4b Chat leads
Llama 2-70B: 7.4 (#310), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Llama 2-70B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1039 | 980 |
| GPQA Diamond | 26.3% | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Llama 2-70B leads
Llama 2-70B: 27.7 (#274), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Llama 2-70B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1045 | 979 |
| LMArena Chinese | 995 | 1024 |
| LMArena German | 1041 | 902 |
| LMArena Russian | 1083 | 952 |
| LMArena French | 1090 | — |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Llama 2-70B leads
Llama 2-70B: 54.9 (#278), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Llama 2-70B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1071 | 978 |
Long Context Llama 2-70B leads
Llama 2-70B: 32.3 (#270), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Llama 2-70B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1062 | 988 |
Writing & Preference Llama 2-70B leads
Llama 2-70B: 32.3 (#279), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Llama 2-70B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1115 | 997 |
| LMArena Creative Writing | 1075 | 969 |
| LMArena Multi-Turn | 1088 | 977 |
Frequently asked questions
Is Llama 2-70B better than Qwen1.5 4b Chat?
Qwen1.5 4b Chat is the stronger model overall, scoring 28.8 to 24.4 on the Noometry Index.
Is Llama 2-70B or Qwen1.5 4b Chat better for coding?
Llama 2-70B scores higher on coding benchmarks: 31.4 versus 29.1 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Qwen1.5 4b Chat has 13.