Model comparison
Llama 3.1-405B vs Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 30.7 on the Noometry Index.
Last verified . 19 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Qwen3-Coder 480B-A35B Instruct in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-Coder 480B-A35B Instruct leads 37.6 to 18.4.
- The biggest single-benchmark swing is WeirdML: 21.4% for Llama 3.1-405B and 41.2% for Qwen3-Coder 480B-A35B Instruct.
Side by side
| Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.7 | 38.1 |
| Released | 2024-07-23 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.50 |
| Output $ / M tokens | — | $7.50 |
| Results tracked | 42 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 33.1 (#262), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 21.4% | 41.2% |
| LMArena Coding | 1291 | 1412 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 21.0 (#140), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 16.8 (#300), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 45% | 49.5% |
| LMArena Hard Prompts | 1269 | 1372 |
| SimpleBench | 23% | — |
| 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 Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 18.4 (#290), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1281 | 1365 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 30.4 (#227), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1243 | 1338 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 40.7 (#214), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1248 | 1346 |
| LMArena Chinese | 1242 | 1357 |
| LMArena French | 1279 | 1398 |
| LMArena German | 1252 | 1325 |
| LMArena Japanese | 1208 | 1310 |
| LMArena Korean | 1184 | 1305 |
| LMArena Russian | 1265 | 1366 |
| LMArena Spanish | 1260 | 1360 |
Instruction Following Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 65.9 (#214), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1259 | 1355 |
| IFEval | 81.1% | — |
Long Context Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 38.4 (#197), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1266 | 1378 |
Writing & Preference Qwen3-Coder 480B-A35B Instruct leads
Llama 3.1-405B: 38.9 (#251), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | Llama 3.1-405B | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1284 | 1357 |
| LMArena Creative Writing | 1262 | 1333 |
| LMArena Multi-Turn | 1297 | 1365 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is the stronger model overall, scoring 38.1 to 30.7 on the Noometry Index.
Is Llama 3.1-405B or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 35.5 versus 33.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Qwen3-Coder 480B-A35B Instruct share?
19 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.