Model comparison
Llama 3.2 1B vs Qwen1.5-7B
Qwen1.5-7B is the stronger model overall, scoring 30.8 to 19.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Qwen1.5-7B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen1.5-7B leads 28.2 to 7.2.
Side by side
| Llama 3.2 1B | Qwen1.5-7B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 19.9 | 30.8 |
| Released | 2024-09-24 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 60K | — |
| Max output | 54K | — |
| Input $ / M tokens | $0.027 | — |
| Output $ / M tokens | $0.20 | — |
| Results tracked | 22 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-7B leads
Llama 3.2 1B: 20.6 (#333), Qwen1.5-7B: 31.6 (#271)
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| LMArena Coding | 1071 | 1107 |
| BigCodeBench Instruct | 8.2% | — |
| BigCodeBench Complete | 11.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 1B: 14.5 (#142), Qwen1.5-7B: —
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10.8% | — |
| BALROG | 6.6% | — |
Reasoning Qwen1.5-7B leads
Llama 3.2 1B: 15.6 (#304), Qwen1.5-7B: 19.5 (#237)
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| LMArena Hard Prompts | 1044 | 1066 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 101.95 | — |
Math Qwen1.5-7B leads
Llama 3.2 1B: 9.7 (#308), Qwen1.5-7B: 29.0 (#222)
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| LMArena Math | 1086 | 1080 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
Knowledge Qwen1.5-7B leads
Llama 3.2 1B: 7.2 (#307), Qwen1.5-7B: 28.2 (#239)
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| LMArena Expert | 1007 | 1055 |
| GPQA Diamond | 23.9% | — |
| MMLU | — | 62.6% |
Multilingual Qwen1.5-7B leads
Llama 3.2 1B: 23.9 (#287), Qwen1.5-7B: 28.6 (#266)
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| LMArena Non-English | 973 | 1058 |
| LMArena Chinese | 958 | 1140 |
| LMArena Russian | 941 | 1006 |
| LMArena German | 1014 | — |
Instruction Following Qwen1.5-7B leads
Llama 3.2 1B: 52.6 (#285), Qwen1.5-7B: 54.4 (#276)
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| LMArena Instruction Following | 1031 | 1058 |
Long Context Qwen1.5-7B leads
Llama 3.2 1B: 31.9 (#269), Qwen1.5-7B: 33.1 (#261)
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| LMArena Longer Query | 1050 | 1090 |
Writing & Preference Qwen1.5-7B leads
Llama 3.2 1B: 21.4 (#305), Qwen1.5-7B: 29.8 (#288)
| Benchmark | Llama 3.2 1B | Qwen1.5-7B |
|---|---|---|
| LMArena Text | 1055 | 1084 |
| LMArena Creative Writing | 1033 | 1035 |
| LMArena Multi-Turn | 1030 | 1061 |
| EQ-Bench Creative Writing | 200 | — |
Frequently asked questions
Is Llama 3.2 1B better than Qwen1.5-7B?
Qwen1.5-7B is the stronger model overall, scoring 30.8 to 19.9 on the Noometry Index.
Is Llama 3.2 1B or Qwen1.5-7B better for coding?
Qwen1.5-7B scores higher on coding benchmarks: 31.6 versus 20.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 1B and Qwen1.5-7B share?
12 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Qwen1.5-7B has 13.