Model comparison
Llama 3.1-8B vs Qwen1.5-72B
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 23.0 on the Noometry Index.
Last verified . 22 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. Llama 3.1-8B scores higher in 2 categories and Qwen1.5-72B in 6 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-72B leads 33.2 to 10.2.
Side by side
| Llama 3.1-8B | Qwen1.5-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 23.0 | 30.8 |
| Released | 2024-07-23 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 43 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-72B leads
Llama 3.1-8B: 20.2 (#340), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 32.8% | 33.2% |
| LMArena Coding | 1195 | 1165 |
| BigCodeBench Complete | 40.5% | 40.3% |
| HumanEval+ | 62.8% | 59.1% |
| MBPP+ | 55.6% | 61.6% |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
Agentic & Tool Use Not comparable
Llama 3.1-8B: 22.5 (#131), Qwen1.5-72B: —
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |
Reasoning Qwen1.5-72B leads
Llama 3.1-8B: 14.9 (#321), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1175 | 1148 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| Epoch Capabilities Index | 116.57 | — |
| PIQA | 81.2% | — |
Math Qwen1.5-72B leads
Llama 3.1-8B: 10.2 (#317), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1179 | 1164 |
| OTIS Mock AIME 2024-2025 | 1.7% | — |
| Omni-MATH | 13.7% | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |
Knowledge Qwen1.5-72B leads
Llama 3.1-8B: 8.0 (#307), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 27% | 28.8% |
| LMArena Expert | 1144 | 1136 |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| BoolQ | 82.8% | — |
| MMLU | 56.1% | — |
Multilingual Too close to call
Llama 3.1-8B: 34.0 (#249), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1148 | 1135 |
| LMArena Chinese | 1151 | 1186 |
| LMArena French | 1177 | 1159 |
| LMArena German | 1144 | 1084 |
| LMArena Japanese | 1061 | 1061 |
| LMArena Korean | 1053 | 1050 |
| LMArena Russian | 1158 | 1104 |
| LMArena Spanish | 1169 | 1110 |
Instruction Following Too close to call
Llama 3.1-8B: 58.9 (#258), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1159 | 1141 |
| IFEval | 74.3% | — |
Long Context Too close to call
Llama 3.1-8B: 35.8 (#238), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1182 | 1157 |
Writing & Preference Qwen1.5-72B leads
Llama 3.1-8B: 29.7 (#290), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Llama 3.1-8B | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1187 | 1166 |
| LMArena Creative Writing | 1154 | 1137 |
| LMArena Multi-Turn | 1172 | 1160 |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
Frequently asked questions
Is Llama 3.1-8B better than Qwen1.5-72B?
Qwen1.5-72B is the stronger model overall, scoring 30.8 to 23.0 on the Noometry Index.
Is Llama 3.1-8B or Qwen1.5-72B better for coding?
Qwen1.5-72B scores higher on coding benchmarks: 31.9 versus 20.2 in the Noometry coding category.
How many benchmarks do Llama 3.1-8B and Qwen1.5-72B share?
22 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Qwen1.5-72B has 22.