Model comparison
Llama 3-70B vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 28.8 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Llama 3-70B scores higher in 1 category and Qwen Max in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen Max leads 30.3 to 20.8.
- The biggest single-benchmark swing is MATH Level 5: 22.6% for Llama 3-70B and 67.2% for Qwen Max.
- Llama 3-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-70B | Qwen Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.8 | 34.7 |
| Released | 2024-04-18 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 31 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
Llama 3-70B: 35.8 (#218), Qwen Max: 30.7 (#292)
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| LMArena Coding | 1206 | 1288 |
| Aider Polyglot | — | 21.8% |
| BigCodeBench Instruct | 43.6% | — |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |
Agentic & Tool Use Not comparable
Llama 3-70B: 21.1 (#139), Qwen Max: —
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| Cybench | 5% | — |
Reasoning Qwen Max leads
Llama 3-70B: 18.0 (#288), Qwen Max: 25.1 (#151)
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1269 |
| Kagi LLM Benchmark | 35.1% | — |
| DTBench | 54.2% | — |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| WinoGrande | 83.5% | — |
Math Qwen Max leads
Llama 3-70B: 12.8 (#305), Qwen Max: 22.3 (#276)
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 4.3% | 16.1% |
| LMArena Math | 1218 | 1275 |
| MATH Level 5 | 22.6% | 67.2% |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Qwen Max leads
Llama 3-70B: 20.8 (#277), Qwen Max: 30.3 (#228)
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| GPQA Diamond | 40.6% | 56.1% |
| LMArena Expert | 1149 | 1248 |
| MMLU | 79.3% | — |
Multilingual Qwen Max leads
Llama 3-70B: 33.6 (#251), Qwen Max: 41.8 (#202)
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| LMArena Non-English | 1142 | 1263 |
| LMArena Chinese | 1114 | 1254 |
| LMArena French | 1232 | 1330 |
| LMArena German | 1169 | 1254 |
| LMArena Japanese | 1017 | 1205 |
| LMArena Korean | 1017 | 1142 |
| LMArena Russian | 1159 | 1274 |
| LMArena Spanish | 1241 | 1290 |
Instruction Following Qwen Max leads
Llama 3-70B: 62.5 (#238), Qwen Max: 66.5 (#208)
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1194 | 1262 |
Long Context Qwen Max leads
Llama 3-70B: 35.6 (#240), Qwen Max: 39.4 (#180)
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1174 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Llama 3-70B: 42.8 (#231), Qwen Max: 47.8 (#205)
| Benchmark | Llama 3-70B | Qwen Max |
|---|---|---|
| LMArena Text | 1221 | 1282 |
| LMArena Creative Writing | 1210 | 1248 |
| LMArena Multi-Turn | 1223 | 1277 |
Frequently asked questions
Is Llama 3-70B better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 28.8 on the Noometry Index.
Is Llama 3-70B or Qwen Max better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 30.7 in the Noometry coding category.
How many benchmarks do Llama 3-70B and Qwen Max share?
20 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Qwen Max has 23.