Model comparison
Llama 3.2 90B vs Qwen2-72B
Qwen2-72B is the stronger model overall, scoring 30.0 to 27.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Llama 3.2 90B scores higher in 2 categories and Qwen2-72B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 11.1.
Side by side
| Llama 3.2 90B | Qwen2-72B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.5 | 30.0 |
| Released | 2024-09-24 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Qwen2-72B: 29.1 (#310)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| LMArena Coding | — | 1196 |
| BigCodeBench Complete | — | 54% |
Agentic & Tool Use Llama 3.2 90B leads
Llama 3.2 90B: 30.0 (#80), Qwen2-72B: 17.0 (#146)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| BALROG | 27.3% | — |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Llama 3.2 90B: 21.7 (#217), Qwen2-72B: 23.2 (#181)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 125.28 |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1191 |
Math Qwen2-72B leads
Llama 3.2 90B: 11.1 (#308), Qwen2-72B: 30.2 (#236)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| MATH Level 5 | 39.4% | 39.1% |
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| LMArena Math | — | 1235 |
Knowledge Too close to call
Llama 3.2 90B: 21.7 (#274), Qwen2-72B: 21.2 (#275)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 41% | 40.8% |
| MMLU | 80.3% | 82.4% |
| LMArena Expert | — | 1171 |
Multimodal Not comparable
Llama 3.2 90B: 25.4 (#124), Qwen2-72B: —
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Qwen2-72B: 35.9 (#244)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Not comparable
Llama 3.2 90B: —, Qwen2-72B: 61.7 (#241)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
Llama 3.2 90B: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Qwen2-72B: 40.8 (#241)
| Benchmark | Llama 3.2 90B | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Llama 3.2 90B better than Qwen2-72B?
Qwen2-72B is the stronger model overall, scoring 30.0 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Qwen2-72B share?
4 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Qwen2-72B has 26.