Model comparison
Llama 13b vs Qwen2.5 72B Instruct
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 24.4 on the Noometry Index.
Last verified . 16 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 16 benchmarks with published results for both. Llama 13b scores higher in 1 category and Qwen2.5 72B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.7 to 13.8.
Side by side
| Llama 13b | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 24.4 | 31.9 |
| Released | 2023-02-24 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 21 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Llama 13b: 21.4 (#337), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 683 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Llama 13b: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Llama 13b: 14.0 (#329), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 728 | 1271 |
| BIG-Bench Hard | 37.9% | 79.8% |
| Epoch Capabilities Index | 100.58 | 129 |
| HellaSwag | 79.2% | 84.8% |
| PIQA | 80.1% | 82.6% |
| WinoGrande | 73% | 82.3% |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| ForecastBench | — | 57.5 |
| LAMBADA | 75.2% | — |
Math Llama 13b leads
Llama 13b: 26.7 (#256), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 838 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | 94.5% |
| MMLU | 47.7% | 85.3% |
| TriviaQA | 77.9% | 71.9% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| BoolQ | 78.7% | — |
| OpenBookQA | 56.4% | — |
Multimodal Not comparable
Llama 13b: —, Qwen2.5 72B Instruct: —
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Qwen2.5 72B Instruct leads
Llama 13b: 16.6 (#297), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 819 | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1256 |
Instruction Following Qwen2.5 72B Instruct leads
Llama 13b: 36.7 (#305), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 781 | 1254 |
| IFEval | — | 80.6% |
Long Context Not comparable
Llama 13b: —, Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Llama 13b: 13.8 (#312), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Llama 13b | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 834 | 1269 |
| LMArena Creative Writing | 794 | 1221 |
| LMArena Multi-Turn | 753 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Llama 13b better than Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 24.4 on the Noometry Index.
Is Llama 13b or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Qwen2.5 72B Instruct share?
16 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Qwen2.5 72B Instruct has 43.