Model comparison
Llama 2-34B vs Qwen-7B
Neither Llama 2-34B nor Qwen-7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
Last verified . 7 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 7 benchmarks with published results for both.
- Qwen-7B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-34B | Qwen-7B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | — | — |
| Released | 2023-07-18 | 2023-09-28 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Reasoning Not comparable
Llama 2-34B: —, Qwen-7B: —
| Benchmark | Llama 2-34B | Qwen-7B |
|---|---|---|
| BIG-Bench Hard | 44.1% | 45% |
| Epoch Capabilities Index | 105.2 | 106.83 |
| PIQA | 81.9% | 77.9% |
| LAMBADA | — | 67.9% |
| WinoGrande | 76.7% | — |
Math Not comparable
Llama 2-34B: —, Qwen-7B: —
| Benchmark | Llama 2-34B | Qwen-7B |
|---|---|---|
| GSM8K | 42.2% | 51.7% |
Knowledge Not comparable
Llama 2-34B: —, Qwen-7B: —
| Benchmark | Llama 2-34B | Qwen-7B |
|---|---|---|
| ARC (AI2) Challenge | 54.5% | 75.3% |
| BoolQ | 83.7% | 76.4% |
| MMLU | 62.6% | 45% |
| OpenBookQA | 58.2% | — |
| TriviaQA | 84.6% | — |
Frequently asked questions
Is Llama 2-34B better than Qwen-7B?
Neither Llama 2-34B nor Qwen-7B has enough public benchmark results to be ranked yet; the rows below show what has been published.
How many benchmarks do Llama 2-34B and Qwen-7B share?
7 benchmarks have published results for both models. Llama 2-34B has 10 scored results on Noometry and Qwen-7B has 8.