Model comparison
Llama 3-70B vs Qwen Plus
Qwen Plus is the stronger model overall, scoring 37.1 to 28.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Llama 3-70B scores higher in 0 categories and Qwen Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen Plus leads 45.1 to 33.6.
- The biggest single-benchmark swing is MATH Level 5: 22.6% for Llama 3-70B and 65.3% for Qwen Plus.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-70B | Qwen Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.8 | 37.1 |
| Released | 2024-04-18 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 31 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Llama 3-70B: 35.8 (#218), Qwen Plus: 38.9 (#167)
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| LMArena Coding | 1206 | 1328 |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Qwen Plus: —
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| Cybench | 5% | — |
Reasoning Qwen Plus leads
Llama 3-70B: 18.0 (#288), Qwen Plus: 28.4 (#107)
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 35.1% | 63.3% |
| LMArena Hard Prompts | 1195 | 1317 |
| DTBench | 54.2% | 81.1% |
| LMCA | — | 24% |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Qwen Plus leads
Llama 3-70B: 12.8 (#305), Qwen Plus: 23.3 (#271)
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 17.8% |
| LMArena Math | 1218 | 1326 |
| MATH Level 5 | 22.6% | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Qwen Plus leads
Llama 3-70B: 20.8 (#277), Qwen Plus: 27.4 (#251)
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| GPQA Diamond | 40.6% | 48.1% |
| LMArena Expert | 1149 | 1328 |
| MMLU | 79.3% | — |
Multilingual Qwen Plus leads
Llama 3-70B: 33.6 (#251), Qwen Plus: 45.1 (#175)
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1142 | 1310 |
| LMArena Chinese | 1114 | 1347 |
| LMArena Japanese | 1017 | 1251 |
| LMArena Russian | 1159 | 1323 |
| LMArena French | 1232 | — |
| LMArena German | 1169 | — |
| LMArena Korean | 1017 | — |
| LMArena Spanish | 1241 | — |
Instruction Following Qwen Plus leads
Llama 3-70B: 62.5 (#238), Qwen Plus: 68.8 (#181)
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1194 | 1303 |
Long Context Qwen Plus leads
Llama 3-70B: 35.6 (#240), Qwen Plus: 40.3 (#158)
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1174 | 1324 |
Writing & Preference Qwen Plus leads
Llama 3-70B: 42.8 (#231), Qwen Plus: 52.2 (#176)
| Benchmark | Llama 3-70B | Qwen Plus |
|---|---|---|
| LMArena Text | 1221 | 1326 |
| LMArena Creative Writing | 1210 | 1293 |
| LMArena Multi-Turn | 1223 | 1336 |
Frequently asked questions
Is Llama 3-70B better than Qwen Plus?
Qwen Plus is the stronger model overall, scoring 37.1 to 28.8 on the Noometry Index.
Is Llama 3-70B or Qwen Plus better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 35.8 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Qwen Plus share?
18 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Qwen Plus has 20.