Model comparison
Llama 3.1-405B vs Qwen1.5 4b Chat
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 28.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Llama 3.1-405B scores higher in 6 categories and Qwen1.5 4b Chat in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama 3.1-405B leads 65.9 to 49.0.
Side by side
| Llama 3.1-405B | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 30.7 | 28.8 |
| Released | 2024-07-23 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Llama 3.1-405B: 33.1 (#262), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1291 | 999 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Qwen1.5 4b Chat: —
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Qwen1.5 4b Chat leads
Llama 3.1-405B: 16.8 (#300), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1269 | 976 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Qwen1.5 4b Chat leads
Llama 3.1-405B: 18.4 (#290), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1281 | 1026 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Llama 3.1-405B leads
Llama 3.1-405B: 30.4 (#227), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1243 | 980 |
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Llama 3.1-405B leads
Llama 3.1-405B: 40.7 (#214), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1248 | 979 |
| LMArena Chinese | 1242 | 1024 |
| LMArena German | 1252 | 902 |
| LMArena Russian | 1265 | 952 |
| LMArena French | 1279 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 65.9 (#214), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1259 | 978 |
| IFEval | 81.1% | — |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1266 | 988 |
Writing & Preference Llama 3.1-405B leads
Llama 3.1-405B: 38.9 (#251), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | Llama 3.1-405B | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1284 | 997 |
| LMArena Creative Writing | 1262 | 969 |
| LMArena Multi-Turn | 1297 | 977 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Qwen1.5 4b Chat?
Llama 3.1-405B is the stronger model overall, scoring 30.7 to 28.8 on the Noometry Index.
Is Llama 3.1-405B or Qwen1.5 4b Chat better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 29.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Qwen1.5 4b Chat has 13.