Model comparison
Llama 2-13B vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Llama 2-13B scores higher in 0 categories and Qwen3.8 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 31.1.
- The biggest single-benchmark swing is DTBench: 42.2% for Llama 2-13B and 92% for Qwen3.8 Max.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-13B | Qwen3.8 Max | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.6 | 56.8 |
| Released | 2023-07-18 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 32 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Llama 2-13B: 30.9 (#291), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1062 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
Agentic & Tool Use Not comparable
Llama 2-13B: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Llama 2-13B: 12.8 (#337), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| Chess Puzzles | 0% | 40% |
| LMArena Hard Prompts | 1051 | 1496 |
| DTBench | 42.2% | 92% |
| Epoch Capabilities Index | 106.17 | 156.41 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Mystery Game Puzzles | — | 38% |
| LMCA | — | 46.2% |
| BIG-Bench Hard | 58.2% | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Qwen3.8 Max leads
Llama 2-13B: 31.1 (#229), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1065 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
| GSM8K | 36.9% | — |
Knowledge Qwen3.8 Max leads
Llama 2-13B: 28.1 (#249), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1030 | 1507 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
| ScienceQA | 55.8% | — |
Multilingual Qwen3.8 Max leads
Llama 2-13B: 26.5 (#279), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1024 | 1472 |
| LMArena Chinese | 1001 | 1538 |
| LMArena French | 1044 | 1503 |
| LMArena German | 1009 | 1483 |
| LMArena Japanese | 894 | 1467 |
| LMArena Korean | 953 | 1461 |
| LMArena Russian | 1055 | 1481 |
| LMArena Spanish | 1087 | 1492 |
Instruction Following Qwen3.8 Max leads
Llama 2-13B: 53.3 (#287), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1045 | 1479 |
Long Context Qwen3.8 Max leads
Llama 2-13B: 32.3 (#269), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1064 | 1489 |
Writing & Preference Qwen3.8 Max leads
Llama 2-13B: 29.8 (#289), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Llama 2-13B | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1084 | 1483 |
| LMArena Creative Writing | 1047 | 1479 |
| LMArena Multi-Turn | 1050 | 1489 |
Frequently asked questions
Is Llama 2-13B better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 29.6 on the Noometry Index.
Is Llama 2-13B or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 30.9 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Qwen3.8 Max share?
20 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Qwen3.8 Max has 39.