Model comparison
Llama 3.1-405B vs Qwen2-72B
Llama 3.1-405B and Qwen2-72B score almost the same on the Noometry Index (30.4 vs 29.5), so choose on price, context window or the category you care about most.
Last verified . 23 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Llama 3.1-405B scores higher in 6 categories and Qwen2-72B in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 27.9 to 17.3.
- The biggest single-benchmark swing is MATH Level 5: 49.8% for Llama 3.1-405B and 39.1% for Qwen2-72B.
Side by side
| Llama 3.1-405B | Qwen2-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.4 | 29.5 |
| Released | 2024-07-23 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 26 |
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: 32.7 (#257), Qwen2-72B: 28.7 (#303)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| WeirdML | 21.4% | 11.3% |
| LMArena Coding | 1291 | 1196 |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Llama 3.1-405B leads
Llama 3.1-405B: 20.9 (#131), Qwen2-72B: 16.9 (#138)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | 7.4% | 1.1% |
| Cybench | 7.5% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Llama 3.1-405B: 16.4 (#293), Qwen2-72B: 22.2 (#184)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1270 | 1191 |
| Epoch Capabilities Index | 128.76 | 125.27 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Qwen2-72B leads
Llama 3.1-405B: 17.3 (#283), Qwen2-72B: 27.9 (#232)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1281 | 1235 |
| MATH Level 5 | 49.8% | 39.1% |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
Knowledge Llama 3.1-405B leads
Llama 3.1-405B: 30.4 (#221), Qwen2-72B: 21.2 (#270)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 50.9% | 40.8% |
| LMArena Expert | 1243 | 1171 |
| MMLU | 84.5% | 82.4% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| TriviaQA | 82.7% | — |
Multilingual Llama 3.1-405B leads
Llama 3.1-405B: 40.9 (#209), Qwen2-72B: 36.0 (#239)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1248 | 1176 |
| LMArena Chinese | 1242 | 1240 |
| LMArena French | 1278 | 1169 |
| LMArena German | 1252 | 1151 |
| LMArena Japanese | 1208 | 1111 |
| LMArena Korean | 1184 | 1083 |
| LMArena Russian | 1265 | 1169 |
| LMArena Spanish | 1259 | 1168 |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 66.1 (#209), Qwen2-72B: 62.0 (#236)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1259 | 1181 |
| IFEval | 81.1% | — |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#192), Qwen2-72B: 36.1 (#230)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1266 | 1193 |
Writing & Preference Qwen2-72B leads
Llama 3.1-405B: 39.1 (#246), Qwen2-72B: 41.0 (#236)
| Benchmark | Llama 3.1-405B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1284 | 1203 |
| LMArena Creative Writing | 1262 | 1181 |
| LMArena Multi-Turn | 1297 | 1195 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Qwen2-72B?
Llama 3.1-405B and Qwen2-72B score almost the same on the Noometry Index (30.4 vs 29.5), so choose on price, context window or the category you care about most.
Is Llama 3.1-405B or Qwen2-72B better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 32.7 versus 28.7 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Qwen2-72B share?
23 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Qwen2-72B has 26.