Model comparison
Llama 3.1-70B vs Qwen-14B
Qwen-14B is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. Llama 3.1-70B scores higher in 5 categories and Qwen-14B in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen-14B leads 28.7 to 12.7.
Side by side
| Llama 3.1-70B | Qwen-14B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 29.4 | 30.8 |
| Released | 2024-07-23 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.40 | — |
| Output $ / M tokens | $0.40 | — |
| Results tracked | 35 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3.1-70B: 29.8 (#292), Qwen-14B: 30.6 (#283)
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| LMArena Coding | 1260 | 1072 |
| WeirdML | 9% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 54.8% | — |
Agentic & Tool Use Not comparable
Llama 3.1-70B: 24.9 (#104), Qwen-14B: —
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |
Reasoning Llama 3.1-70B leads
Llama 3.1-70B: 20.8 (#215), Qwen-14B: 18.7 (#255)
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1241 | 1027 |
| Epoch Capabilities Index | 125.91 | 112.8 |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Qwen-14B leads
Llama 3.1-70B: 12.7 (#298), Qwen-14B: 28.7 (#224)
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| LMArena Math | 1252 | 1068 |
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| MATH Level 5 | 36.7% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Llama 3.1-70B: 24.1 (#264), Qwen-14B: —
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| MMLU | 80.1% | 66.3% |
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| LMArena Expert | 1209 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
Multilingual Llama 3.1-70B leads
Llama 3.1-70B: 38.9 (#220), Qwen-14B: 27.7 (#270)
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1219 | 1042 |
| LMArena Chinese | 1215 | 1077 |
| LMArena French | 1260 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1253 | — |
Instruction Following Llama 3.1-70B leads
Llama 3.1-70B: 65.5 (#218), Qwen-14B: 52.6 (#284)
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1231 | 1031 |
| IFEval | 82.1% | — |
Long Context Llama 3.1-70B leads
Llama 3.1-70B: 37.6 (#208), Qwen-14B: 31.3 (#276)
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1241 | 1029 |
Writing & Preference Llama 3.1-70B leads
Llama 3.1-70B: 35.6 (#262), Qwen-14B: 27.8 (#294)
| Benchmark | Llama 3.1-70B | Qwen-14B |
|---|---|---|
| LMArena Text | 1261 | 1051 |
| LMArena Creative Writing | 1232 | 1028 |
| LMArena Multi-Turn | 1256 | 1022 |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
Frequently asked questions
Is Llama 3.1-70B better than Qwen-14B?
Qwen-14B is the stronger model overall, scoring 30.8 to 29.4 on the Noometry Index.
Is Llama 3.1-70B or Qwen-14B better for coding?
They score almost the same on coding (29.8 vs 30.6); test both on your own repository before choosing.
How many benchmarks do Llama 3.1-70B and Qwen-14B share?
12 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Qwen-14B has 18.