Model comparison
Llama 3.2 3B vs Qwen1.5 4b Chat
Llama 3.2 3B and Qwen1.5 4b Chat score almost the same on the Noometry Index (28.9 vs 28.8), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Llama 3.2 3B scores higher in 7 categories and Qwen1.5 4b Chat in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3.2 3B leads 56.0 to 49.0.
Side by side
| Llama 3.2 3B | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 28.9 | 28.8 |
| Released | 2024-09-24 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5 4b Chat leads
Llama 3.2 3B: 27.6 (#319), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1098 | 999 |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Qwen1.5 4b Chat: —
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Llama 3.2 3B leads
Llama 3.2 3B: 21.0 (#228), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1095 | 976 |
Math Llama 3.2 3B leads
Llama 3.2 3B: 32.4 (#214), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1126 | 1026 |
Knowledge Llama 3.2 3B leads
Llama 3.2 3B: 29.7 (#235), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1090 | 980 |
Multilingual Llama 3.2 3B leads
Llama 3.2 3B: 26.2 (#281), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1019 | 979 |
| LMArena Chinese | 1017 | 1024 |
| LMArena German | 1056 | 902 |
| LMArena Russian | 949 | 952 |
Instruction Following Llama 3.2 3B leads
Llama 3.2 3B: 56.0 (#275), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1089 | 978 |
Long Context Llama 3.2 3B leads
Llama 3.2 3B: 33.4 (#261), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1100 | 988 |
Writing & Preference Too close to call
Llama 3.2 3B: 24.7 (#307), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Llama 3.2 3B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1110 | 997 |
| LMArena Creative Writing | 1094 | 969 |
| LMArena Multi-Turn | 1105 | 977 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Qwen1.5 4b Chat?
Llama 3.2 3B and Qwen1.5 4b Chat score almost the same on the Noometry Index (28.9 vs 28.8), so choose on price, context window or the category you care about most.
Is Llama 3.2 3B or Qwen1.5 4b Chat better for coding?
Qwen1.5 4b Chat scores higher on coding benchmarks: 29.1 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Qwen1.5 4b Chat has 13.