Model comparison
Llama 2-7B vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 29.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and Qwen3.7 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.7 Plus leads 64.3 to 28.0.
- The biggest single-benchmark swing is Chess Puzzles: 0% for Llama 2-7B and 24% for Qwen3.7 Plus.
- Llama 2-7B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-7B | Qwen3.7 Plus | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.1 | 45.3 |
| Released | 2023-07-18 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.60 |
| Results tracked | 29 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
Llama 2-7B: 29.2 (#307), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1002 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
Agentic & Tool Use Not comparable
Llama 2-7B: —, Qwen3.7 Plus: 21.4 (#138)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
Llama 2-7B: 15.7 (#312), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| Chess Puzzles | 0% | 24% |
| LMArena Hard Prompts | 1009 | 1460 |
| Epoch Capabilities Index | 99.06 | 147.37 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| BIG-Bench Hard | 39.2% | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Qwen3.7 Plus leads
Llama 2-7B: 30.7 (#233), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1042 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| GSM8K | 16.7% | — |
Knowledge Qwen3.7 Plus leads
Llama 2-7B: 28.2 (#248), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1036 | 1467 |
| GPQA Diamond | — | 87.9% |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
| ScienceQA | 43.1% | — |
Multilingual Qwen3.7 Plus leads
Llama 2-7B: 23.8 (#293), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 973 | 1445 |
| LMArena Chinese | 973 | 1510 |
| LMArena French | 970 | 1473 |
| LMArena German | 978 | 1471 |
| LMArena Russian | 995 | 1457 |
| LMArena Spanish | 1007 | 1457 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
Instruction Following Qwen3.7 Plus leads
Llama 2-7B: 50.8 (#298), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1006 | 1440 |
Long Context Qwen3.7 Plus leads
Llama 2-7B: 30.4 (#287), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 999 | 1455 |
Writing & Preference Qwen3.7 Plus leads
Llama 2-7B: 28.0 (#298), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | Llama 2-7B | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1053 | 1455 |
| LMArena Creative Writing | 1033 | 1439 |
| LMArena Multi-Turn | 1029 | 1460 |
Frequently asked questions
Is Llama 2-7B better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 29.1 on the Noometry Index.
Is Llama 2-7B or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 29.2 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Qwen3.7 Plus share?
17 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Qwen3.7 Plus has 32.