Model comparison
Llama 3.1-405B vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.7 on the Noometry Index.
Last verified . 21 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 18.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 9.7% for Llama 3.1-405B and 100% for Qwen3.8 Max.
- Llama 3.1-405B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1-405B | Qwen3.8 Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.7 | 56.8 |
| Released | 2024-07-23 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 42 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Llama 3.1-405B: 33.1 (#262), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1291 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| WeirdML | 21.4% | — |
Agentic & Tool Use Qwen3.8 Max leads
Llama 3.1-405B: 21.0 (#140), Qwen3.8 Max: 45.4 (#14)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| TheAgentCompany | 7.4% | — |
| τ²-bench Banking | — | 55.1% |
| Cybench | 7.5% | — |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Llama 3.1-405B: 16.8 (#300), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1496 |
| DTBench | 61.4% | 92% |
| Epoch Capabilities Index | 128.75 | 156.41 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| LMCA | — | 46.2% |
| BIG-Bench Hard | 82.9% | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Qwen3.8 Max leads
Llama 3.1-405B: 18.4 (#290), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 100% |
| LMArena Math | 1281 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Qwen3.8 Max leads
Llama 3.1-405B: 30.4 (#227), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 50.9% | 92.7% |
| LMArena Expert | 1243 | 1507 |
| SimpleQA Verified | — | 47.3% |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multimodal Not comparable
Llama 3.1-405B: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Llama 3.1-405B: 40.7 (#214), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1248 | 1472 |
| LMArena Chinese | 1242 | 1538 |
| LMArena French | 1279 | 1503 |
| LMArena German | 1252 | 1483 |
| LMArena Japanese | 1208 | 1467 |
| LMArena Korean | 1184 | 1461 |
| LMArena Russian | 1265 | 1481 |
| LMArena Spanish | 1260 | 1492 |
Instruction Following Qwen3.8 Max leads
Llama 3.1-405B: 65.9 (#214), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1259 | 1479 |
| IFEval | 81.1% | — |
Long Context Qwen3.8 Max leads
Llama 3.1-405B: 38.4 (#197), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1266 | 1489 |
Writing & Preference Qwen3.8 Max leads
Llama 3.1-405B: 38.9 (#251), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Llama 3.1-405B | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1284 | 1483 |
| LMArena Creative Writing | 1262 | 1479 |
| LMArena Multi-Turn | 1297 | 1489 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Qwen3.8 Max share?
21 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Qwen3.8 Max has 39.