Model comparison
Llama 3.1-405B vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 30.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Qwen3.7 Max in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.3 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 9.7% for Llama 3.1-405B and 95.6% for Qwen3.7 Max.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | Qwen3.7 Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.4 | 51.4 |
| Released | 2024-07-23 | 2026-05-19 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 42 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
Llama 3.1-405B: 32.7 (#257), Qwen3.7 Max: 50.2 (#43)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1291 | 1498 |
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| WeirdML | 21.4% | — |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use Too close to call
Llama 3.1-405B: 20.9 (#131), Qwen3.7 Max: 21.8 (#129)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
| GBAEval | — | 0.4% |
Reasoning Qwen3.7 Max leads
Llama 3.1-405B: 16.4 (#293), Qwen3.7 Max: 48.4 (#36)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| SimpleBench | 23% | 70.4% |
| LMArena Hard Prompts | 1270 | 1483 |
| DTBench | 61.4% | 92.3% |
| Epoch Capabilities Index | 128.76 | 153.74 |
| Kagi LLM Benchmark | 45% | — |
| NYT Connections (extended) | — | 85.1% |
| CritPt | — | 13.4% |
| Chess Puzzles | — | 19% |
| EBR-Bench | — | 9.5% |
| Mystery Game Puzzles | — | 32% |
| LMCA | — | 44% |
| BIG-Bench Hard | 82.9% | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Qwen3.7 Max leads
Llama 3.1-405B: 17.3 (#283), Qwen3.7 Max: 62.3 (#26)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 95.6% |
| LMArena Math | 1281 | 1488 |
| FrontierMath (Tiers 1-3) | — | 64.6% |
| FrontierMath Tier 4 | — | 34.1% |
| ProofBench | — | 26% |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Qwen3.7 Max leads
Llama 3.1-405B: 30.4 (#221), Qwen3.7 Max: 61.7 (#24)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 50.9% | 90.9% |
| LMArena Expert | 1243 | 1488 |
| SimpleQA Verified | — | 55.8% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Qwen3.7 Max leads
Llama 3.1-405B: 40.9 (#209), Qwen3.7 Max: 57.1 (#13)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1248 | 1475 |
| LMArena Chinese | 1242 | 1533 |
| LMArena Russian | 1265 | 1482 |
| LMArena French | 1278 | — |
| LMArena German | 1252 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1259 | — |
Instruction Following Qwen3.7 Max leads
Llama 3.1-405B: 66.1 (#209), Qwen3.7 Max: 76.9 (#34)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1259 | 1460 |
| IFEval | 81.1% | — |
Long Context Qwen3.7 Max leads
Llama 3.1-405B: 38.4 (#192), Qwen3.7 Max: 45.4 (#34)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1266 | 1484 |
Writing & Preference Qwen3.7 Max leads
Llama 3.1-405B: 39.1 (#246), Qwen3.7 Max: 65.2 (#52)
| Benchmark | Llama 3.1-405B | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1284 | 1476 |
| LMArena Creative Writing | 1262 | 1450 |
| LMArena Multi-Turn | 1297 | 1482 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is Llama 3.1-405B better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.4 to 30.4 on the Noometry Index.
Is Llama 3.1-405B or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.2 versus 32.7 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Qwen3.7 Max share?
17 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Qwen3.7 Max has 33.