Model comparison
Llama 2-13B vs Qwen3.5 122B-A10B
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 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 Qwen3.5 122B-A10B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.5 122B-A10B leads 60.0 to 29.8.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 84.3% for Qwen3.5 122B-A10B.
Side by side
| Llama 2-13B | Qwen3.5 122B-A10B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 42.1 |
| Released | 2023-07-18 | 2026-02-23 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $3.20 |
| Results tracked | 32 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 122B-A10B leads
Llama 2-13B: 30.9 (#291), Qwen3.5 122B-A10B: 39.1 (#162)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Coding | 1062 | 1436 |
| LMArena WebDev | — | 1360 |
| SciCode | — | 35.6% |
Reasoning Qwen3.5 122B-A10B leads
Llama 2-13B: 12.8 (#337), Qwen3.5 122B-A10B: 27.2 (#123)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1421 |
| DTBench | 42.2% | 84.3% |
| NYT Connections (extended) | — | 51.7% |
| CritPt | — | 0.9% |
| Chess Puzzles | 0% | — |
| Thematic Generalization | — | 51.2% |
| Mystery Game Puzzles | — | 17% |
| LMCA | — | 32.2% |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 106.17 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Qwen3.5 122B-A10B leads
Llama 2-13B: 31.1 (#229), Qwen3.5 122B-A10B: 39.1 (#112)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Math | 1065 | 1432 |
| GSM8K | 36.9% | — |
Knowledge Qwen3.5 122B-A10B leads
Llama 2-13B: 28.1 (#249), Qwen3.5 122B-A10B: 38.8 (#142)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Expert | 1030 | 1432 |
| Vectara Hallucination Rate | — | 11.2% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Qwen3.5 122B-A10B: 39.6 (#57)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Vision | — | 1245 |
| ScienceQA | 55.8% | — |
Multilingual Qwen3.5 122B-A10B leads
Llama 2-13B: 26.5 (#279), Qwen3.5 122B-A10B: 51.6 (#107)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Non-English | 1024 | 1400 |
| LMArena Chinese | 1001 | 1462 |
| LMArena French | 1044 | 1442 |
| LMArena German | 1009 | 1426 |
| LMArena Japanese | 894 | 1367 |
| LMArena Korean | 953 | 1352 |
| LMArena Russian | 1055 | 1400 |
| LMArena Spanish | 1087 | 1424 |
Instruction Following Qwen3.5 122B-A10B leads
Llama 2-13B: 53.3 (#287), Qwen3.5 122B-A10B: 73.8 (#115)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Instruction Following | 1045 | 1399 |
Long Context Qwen3.5 122B-A10B leads
Llama 2-13B: 32.3 (#269), Qwen3.5 122B-A10B: 43.0 (#109)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Longer Query | 1064 | 1410 |
Writing & Preference Qwen3.5 122B-A10B leads
Llama 2-13B: 29.8 (#289), Qwen3.5 122B-A10B: 60.0 (#105)
| Benchmark | Llama 2-13B | Qwen3.5 122B-A10B |
|---|---|---|
| LMArena Text | 1084 | 1417 |
| LMArena Creative Writing | 1047 | 1368 |
| LMArena Multi-Turn | 1050 | 1416 |
Frequently asked questions
Is Llama 2-13B better than Qwen3.5 122B-A10B?
Qwen3.5 122B-A10B is the stronger model overall, scoring 42.1 to 29.6 on the Noometry Index.
Is Llama 2-13B or Qwen3.5 122B-A10B better for coding?
Qwen3.5 122B-A10B scores higher on coding benchmarks: 39.1 versus 30.9 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Qwen3.5 122B-A10B share?
18 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Qwen3.5 122B-A10B has 27.