Model comparison
Llama 2-13B vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 29.6 on the Noometry Index.
Last verified . 18 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Llama 2-13B scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5-Max leads 55.4 to 29.8.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-13B | Qwen2.5-Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 40.7 |
| Released | 2023-07-18 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Llama 2-13B: 30.9 (#291), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1062 | 1359 |
| LiveBench Coding | — | 64.4% |
Reasoning Qwen2.5-Max leads
Llama 2-13B: 12.8 (#337), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1360 |
| Epoch Capabilities Index | 106.17 | 132.53 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 42.2% | — |
| LiveBench Data Analysis | — | 67.9% |
| BIG-Bench Hard | 58.2% | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| LiveBench | — | 62.3% |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Qwen2.5-Max leads
Llama 2-13B: 31.1 (#229), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1065 | 1369 |
| LiveBench Math | — | 58.4% |
| GSM8K | 36.9% | — |
Knowledge Qwen2.5-Max leads
Llama 2-13B: 28.1 (#249), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1030 | 1337 |
| Confabulations | — | 21.8% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Qwen2.5-Max: —
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Qwen2.5-Max leads
Llama 2-13B: 26.5 (#279), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1024 | 1352 |
| LMArena Chinese | 1001 | 1382 |
| LMArena French | 1044 | 1396 |
| LMArena German | 1009 | 1350 |
| LMArena Japanese | 894 | 1300 |
| LMArena Korean | 953 | 1304 |
| LMArena Russian | 1055 | 1353 |
| LMArena Spanish | 1087 | 1377 |
Instruction Following Qwen2.5-Max leads
Llama 2-13B: 53.3 (#287), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1045 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
Llama 2-13B: 32.3 (#269), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1064 | 1358 |
Writing & Preference Qwen2.5-Max leads
Llama 2-13B: 29.8 (#289), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Llama 2-13B | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1084 | 1367 |
| LMArena Creative Writing | 1047 | 1339 |
| LMArena Multi-Turn | 1050 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Llama 2-13B better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 29.6 on the Noometry Index.
Is Llama 2-13B or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 30.9 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Qwen2.5-Max share?
18 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Qwen2.5-Max has 27.