Model comparison
Llama 3.1-405B vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 38.8 to 30.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Llama 3.1-405B scores higher in 0 categories and Qwen3 32B in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 32B leads 37.9 to 17.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 9.7% for Llama 3.1-405B and 66.9% for Qwen3 32B.
Side by side
| Llama 3.1-405B | Qwen3 32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.4 | 38.8 |
| Released | 2024-07-23 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 42 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Llama 3.1-405B: 32.7 (#257), Qwen3 32B: 37.3 (#184)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| LMArena Coding | 1291 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
| WeirdML | 21.4% | — |
Agentic & Tool Use Qwen3 32B leads
Llama 3.1-405B: 20.9 (#131), Qwen3 32B: 32.3 (#58)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Qwen3 32B leads
Llama 3.1-405B: 16.4 (#293), Qwen3 32B: 19.6 (#233)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| Kagi LLM Benchmark | 45% | 54.9% |
| LMArena Hard Prompts | 1270 | 1335 |
| DTBench | 61.4% | 67.5% |
| Epoch Capabilities Index | 128.76 | 138.51 |
| SimpleBench | 23% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| LMCA | — | 17.3% |
| BIG-Bench Hard | 82.9% | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Qwen3 32B leads
Llama 3.1-405B: 17.3 (#283), Qwen3 32B: 37.9 (#89)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 9.7% | 66.9% |
| LMArena Math | 1281 | 1399 |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Qwen3 32B leads
Llama 3.1-405B: 30.4 (#221), Qwen3 32B: 40.0 (#112)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| GPQA Diamond | 50.9% | 65.7% |
| LMArena Expert | 1243 | 1362 |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| Vectara Hallucination Rate | — | 5.9% |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Qwen3 32B leads
Llama 3.1-405B: 40.9 (#209), Qwen3 32B: 45.8 (#162)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 1248 | 1317 |
| LMArena Chinese | 1242 | 1357 |
| LMArena German | 1252 | 1341 |
| LMArena Russian | 1265 | 1311 |
| LMArena French | 1278 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1259 | — |
Instruction Following Qwen3 32B leads
Llama 3.1-405B: 66.1 (#209), Qwen3 32B: 69.1 (#174)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 1259 | 1305 |
| IFEval | 81.1% | — |
Long Context Qwen3 32B leads
Llama 3.1-405B: 38.4 (#192), Qwen3 32B: 43.7 (#83)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| LMArena Longer Query | 1266 | 1327 |
| Fiction.LiveBench | — | 74.2% |
Writing & Preference Qwen3 32B leads
Llama 3.1-405B: 39.1 (#246), Qwen3 32B: 53.1 (#158)
| Benchmark | Llama 3.1-405B | Qwen3 32B |
|---|---|---|
| LMArena Text | 1284 | 1340 |
| LMArena Creative Writing | 1262 | 1297 |
| LMArena Multi-Turn | 1297 | 1331 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 38.8 to 30.4 on the Noometry Index.
Is Llama 3.1-405B or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.3 versus 32.7 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Qwen3 32B share?
18 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Qwen3 32B has 26.