Model comparison
Llama 3.1-405B vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 30.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Llama 3.1-405B scores higher in 2 categories and Qwen Max in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen Max leads 47.8 to 38.9.
- The biggest single-benchmark swing is MATH Level 5: 49.8% for Llama 3.1-405B and 67.2% for Qwen Max.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | Qwen Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.7 | 34.7 |
| Released | 2024-07-23 | 2024-04-03 |
| Weights | Open | Proprietary |
| Context window | — | 33K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.60 |
| Output $ / M tokens | — | $6.40 |
| Results tracked | 42 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Llama 3.1-405B: 33.1 (#262), Qwen Max: 30.7 (#292)
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| LMArena Coding | 1291 | 1288 |
| Aider Polyglot | — | 21.8% |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Qwen Max: —
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Qwen Max leads
Llama 3.1-405B: 16.8 (#300), Qwen Max: 25.1 (#151)
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1269 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Qwen Max leads
Llama 3.1-405B: 18.4 (#290), Qwen Max: 22.3 (#276)
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 16.1% |
| LMArena Math | 1281 | 1275 |
| MATH Level 5 | 49.8% | 67.2% |
| Omni-MATH | 24.9% | — |
| FrontierMath (Feb 2025 set) | — | 1% |
Knowledge Too close to call
Llama 3.1-405B: 30.4 (#227), Qwen Max: 30.3 (#228)
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| GPQA Diamond | 50.9% | 56.1% |
| LMArena Expert | 1243 | 1248 |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Qwen Max leads
Llama 3.1-405B: 40.7 (#214), Qwen Max: 41.8 (#202)
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| LMArena Non-English | 1248 | 1263 |
| LMArena Chinese | 1242 | 1254 |
| LMArena French | 1279 | 1330 |
| LMArena German | 1252 | 1254 |
| LMArena Japanese | 1208 | 1205 |
| LMArena Korean | 1184 | 1142 |
| LMArena Russian | 1265 | 1274 |
| LMArena Spanish | 1260 | 1290 |
Instruction Following Too close to call
Llama 3.1-405B: 65.9 (#214), Qwen Max: 66.5 (#208)
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1259 | 1262 |
| IFEval | 81.1% | — |
Long Context Qwen Max leads
Llama 3.1-405B: 38.4 (#197), Qwen Max: 39.4 (#180)
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1266 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
Llama 3.1-405B: 38.9 (#251), Qwen Max: 47.8 (#205)
| Benchmark | Llama 3.1-405B | Qwen Max |
|---|---|---|
| LMArena Text | 1284 | 1282 |
| LMArena Creative Writing | 1262 | 1248 |
| LMArena Multi-Turn | 1297 | 1277 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Qwen Max better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 30.7 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Qwen Max share?
20 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Qwen Max has 23.