Model comparison
Llama 13b vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 23.9 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 Qwen3.8 27B in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.9 to 13.9.
Side by side
| Llama 13b | Qwen3.8 27B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.9 | 45.3 |
| Released | 2023-02-24 | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 21 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Llama 13b: 20.9 (#332), Qwen3.8 27B: 50.3 (#42)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 683 | 1487 |
| LMArena WebDev | — | 1592 |
| SciCode | — | 46.6% |
Reasoning Qwen3.8 27B leads
Llama 13b: 13.4 (#327), Qwen3.8 27B: 31.5 (#71)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 728 | 1459 |
| Epoch Capabilities Index | 100.09 | 149.38 |
| NYT Connections (extended) | — | 54.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| BIG-Bench Hard | 37.9% | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Qwen3.8 27B leads
Llama 13b: 24.4 (#259), Qwen3.8 27B: 35.7 (#139)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 838 | 1453 |
| ProofBench | — | 16% |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Qwen3.8 27B: 40.9 (#105)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | — | 1482 |
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Qwen3.8 27B: 40.5 (#36)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1270 |
| ScienceQA | 43.3% | — |
Multilingual Qwen3.8 27B leads
Llama 13b: 16.8 (#292), Qwen3.8 27B: 54.0 (#54)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 819 | 1431 |
| LMArena Chinese | — | 1504 |
| LMArena French | — | 1468 |
| LMArena German | — | 1435 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1389 |
| LMArena Russian | — | 1421 |
| LMArena Spanish | — | 1444 |
Instruction Following Qwen3.8 27B leads
Llama 13b: 36.9 (#300), Qwen3.8 27B: 75.8 (#54)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 781 | 1436 |
Long Context Not comparable
Llama 13b: —, Qwen3.8 27B: 44.3 (#66)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | — | 1448 |
Writing & Preference Qwen3.8 27B leads
Llama 13b: 13.9 (#307), Qwen3.8 27B: 65.9 (#41)
| Benchmark | Llama 13b | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 834 | 1441 |
| LMArena Creative Writing | 794 | 1382 |
| LMArena Multi-Turn | 753 | 1443 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Llama 13b better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 23.9 on the Noometry Index.
Is Llama 13b or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 20.9 in the Noometry coding category.
How many benchmarks do Llama 13b and Qwen3.8 27B share?
9 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Qwen3.8 27B has 28.