Model comparison
Llama 13b vs Qwen3 32B
Qwen3 32B is the stronger model overall, scoring 39.2 to 24.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Qwen3 32B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3 32B leads 52.9 to 13.8.
Side by side
| Llama 13b | Qwen3 32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 24.4 | 39.2 |
| Released | 2023-02-24 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 21 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 32B leads
Llama 13b: 21.4 (#337), Qwen3 32B: 37.7 (#190)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| LMArena Coding | 683 | 1358 |
| Aider Polyglot | — | 40% |
| SciCode | — | 35.4% |
Agentic & Tool Use Not comparable
Llama 13b: —, Qwen3 32B: 32.6 (#62)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 48.7% |
Reasoning Qwen3 32B leads
Llama 13b: 14.0 (#329), Qwen3 32B: 20.2 (#241)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1334 |
| Epoch Capabilities Index | 100.58 | 138.51 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 5% |
| DTBench | — | 67.5% |
| LMCA | — | 17.3% |
| BIG-Bench Hard | 37.9% | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Qwen3 32B leads
Llama 13b: 26.7 (#256), Qwen3 32B: 39.7 (#99)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| LMArena Math | 838 | 1399 |
| OTIS Mock AIME 2024-2025 | — | 66.9% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Qwen3 32B: 40.0 (#125)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| GPQA Diamond | — | 65.7% |
| Vectara Hallucination Rate | — | 5.9% |
| LMArena Expert | — | 1362 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Qwen3 32B: —
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Qwen3 32B leads
Llama 13b: 16.6 (#297), Qwen3 32B: 45.6 (#167)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| LMArena Non-English | 819 | 1317 |
| LMArena Chinese | — | 1357 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1311 |
Instruction Following Qwen3 32B leads
Llama 13b: 36.7 (#305), Qwen3 32B: 68.9 (#179)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| LMArena Instruction Following | 781 | 1305 |
Long Context Not comparable
Llama 13b: —, Qwen3 32B: 43.8 (#87)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| Fiction.LiveBench | — | 74.2% |
| LMArena Longer Query | — | 1327 |
Writing & Preference Qwen3 32B leads
Llama 13b: 13.8 (#312), Qwen3 32B: 52.9 (#163)
| Benchmark | Llama 13b | Qwen3 32B |
|---|---|---|
| LMArena Text | 834 | 1340 |
| LMArena Creative Writing | 794 | 1297 |
| LMArena Multi-Turn | 753 | 1331 |
Frequently asked questions
Is Llama 13b better than Qwen3 32B?
Qwen3 32B is the stronger model overall, scoring 39.2 to 24.4 on the Noometry Index.
Is Llama 13b or Qwen3 32B better for coding?
Qwen3 32B scores higher on coding benchmarks: 37.7 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Qwen3 32B share?
9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Qwen3 32B has 26.