Model comparison
Llama 2-70B vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 24.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Llama 2-70B scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Plus leads 27.4 to 7.4.
- The biggest single-benchmark swing is MATH Level 5: 3.3% for Llama 2-70B and 65.3% for Qwen Plus.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-70B | Qwen Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 24.4 | 37.1 |
| Released | 2023-07-18 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 35 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Llama 2-70B: 31.4 (#286), Qwen Plus: 38.9 (#167)
| Benchmark | Llama 2-70B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1079 | 1328 |
Reasoning Qwen Plus leads
Llama 2-70B: 14.4 (#325), Qwen Plus: 28.4 (#107)
| Benchmark | Llama 2-70B | Qwen Plus |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1317 |
| DTBench | 41.6% | 81.1% |
| Kagi LLM Benchmark | — | 63.3% |
| LMCA | — | 24% |
| 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 Qwen Plus leads
Llama 2-70B: 8.1 (#326), Qwen Plus: 23.3 (#271)
| Benchmark | Llama 2-70B | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0% | 17.8% |
| LMArena Math | 1091 | 1326 |
| MATH Level 5 | 3.3% | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
| GSM8K | 69.6% | — |
Knowledge Qwen Plus leads
Llama 2-70B: 7.4 (#310), Qwen Plus: 27.4 (#251)
| Benchmark | Llama 2-70B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 26.3% | 48.1% |
| LMArena Expert | 1039 | 1328 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Qwen Plus leads
Llama 2-70B: 27.7 (#274), Qwen Plus: 45.1 (#175)
| Benchmark | Llama 2-70B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1045 | 1310 |
| LMArena Chinese | 995 | 1347 |
| LMArena Japanese | 927 | 1251 |
| LMArena Russian | 1083 | 1323 |
| LMArena French | 1090 | — |
| LMArena German | 1041 | — |
| LMArena Korean | 964 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Qwen Plus leads
Llama 2-70B: 54.9 (#278), Qwen Plus: 68.8 (#181)
| Benchmark | Llama 2-70B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1071 | 1303 |
Long Context Qwen Plus leads
Llama 2-70B: 32.3 (#270), Qwen Plus: 40.3 (#158)
| Benchmark | Llama 2-70B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1062 | 1324 |
Writing & Preference Qwen Plus leads
Llama 2-70B: 32.3 (#279), Qwen Plus: 52.2 (#176)
| Benchmark | Llama 2-70B | Qwen Plus |
|---|---|---|
| LMArena Text | 1115 | 1326 |
| LMArena Creative Writing | 1075 | 1293 |
| LMArena Multi-Turn | 1088 | 1336 |
Frequently asked questions
Is Llama 2-70B better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 24.4 on the Noometry Index.
Is Llama 2-70B or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 31.4 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Qwen Plus share?
17 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Qwen Plus has 20.