Model comparison
Llama 13b vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 24.4 on the Noometry Index.
Last verified . 14 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Qwen2.5-Coder-32B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Coder-32B leads 41.6 to 13.8.
Side by side
| Llama 13b | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 24.4 | 33.4 |
| Released | 2023-02-24 | 2024-09-18 |
| Weights | Open | Open |
| Context window | — | 33K |
| Max output | — | 29K |
| Input $ / M tokens | — | $0.66 |
| Output $ / M tokens | — | $1 |
| Results tracked | 21 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Coder-32B leads
Llama 13b: 21.4 (#337), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 683 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Qwen2.5-Coder-32B leads
Llama 13b: 14.0 (#329), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1251 |
| Epoch Capabilities Index | 100.58 | 119.49 |
| HellaSwag | 79.2% | 83% |
| WinoGrande | 73% | 80.8% |
| LiveBench Reasoning | — | 42.1% |
| LiveBench Data Analysis | — | 49.9% |
| BIG-Bench Hard | 37.9% | — |
| LAMBADA | 75.2% | — |
| LiveBench | — | 46.2% |
| PIQA | 80.1% | — |
Math Qwen2.5-Coder-32B leads
Llama 13b: 26.7 (#256), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 838 | 1251 |
| GSM8K | 20.6% | 93% |
| LiveBench Math | — | 46.6% |
Knowledge Not comparable
Llama 13b: —, Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | 70.5% |
| MMLU | 47.7% | 79.1% |
| LMArena Expert | — | 1221 |
| BoolQ | 78.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Qwen2.5-Coder-32B: —
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Qwen2.5-Coder-32B leads
Llama 13b: 16.6 (#297), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 819 | 1205 |
| LMArena Chinese | — | 1222 |
| LMArena Russian | — | 1228 |
Instruction Following Qwen2.5-Coder-32B leads
Llama 13b: 36.7 (#305), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 781 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context Not comparable
Llama 13b: —, Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | — | 1251 |
Writing & Preference Qwen2.5-Coder-32B leads
Llama 13b: 13.8 (#312), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Llama 13b | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 834 | 1230 |
| LMArena Creative Writing | 794 | 1174 |
| LMArena Multi-Turn | 753 | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Llama 13b better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B is the stronger model overall, scoring 33.4 to 24.4 on the Noometry Index.
Is Llama 13b or Qwen2.5-Coder-32B better for coding?
Qwen2.5-Coder-32B scores higher on coding benchmarks: 22.6 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Qwen2.5-Coder-32B share?
14 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Qwen2.5-Coder-32B has 31.