Model comparison
Llama 3.2 90B vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 27.5 on the Noometry Index.
Last verified . 2 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 2 benchmarks with published results for both. Llama 3.2 90B scores higher in 0 categories and Qwen3.8 27B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 27B leads 37.1 to 11.1.
Side by side
| Llama 3.2 90B | Qwen3.8 27B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.5 | 46.0 |
| Released | 2024-09-24 | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.04 |
| Output $ / M tokens | — | $2.30 |
| Results tracked | 9 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Qwen3.8 27B: 50.5 (#44)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| LMArena Coding | — | 1482 |
Agentic & Tool Use Qwen3.8 27B leads
Llama 3.2 90B: 30.0 (#80), Qwen3.8 27B: 32.9 (#57)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
| BALROG | 27.3% | — |
Reasoning Qwen3.8 27B leads
Llama 3.2 90B: 21.7 (#217), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 149.38 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1460 |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
Math Qwen3.8 27B leads
Llama 3.2 90B: 11.1 (#308), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | — |
| ProofBench | — | 16% |
| LMArena Math | — | 1456 |
| MATH Level 5 | 39.4% | — |
Knowledge Qwen3.8 27B leads
Llama 3.2 90B: 21.7 (#274), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| GPQA Diamond | 41% | — |
| LMArena Expert | — | 1482 |
| MMLU | 80.3% | — |
Multimodal Qwen3.8 27B leads
Llama 3.2 90B: 25.4 (#124), Qwen3.8 27B: 41.3 (#37)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | 1000 | 1271 |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Qwen3.8 27B: 53.7 (#60)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1504 |
| LMArena French | — | 1465 |
| LMArena German | — | 1438 |
| LMArena Japanese | — | 1384 |
| LMArena Korean | — | 1393 |
| LMArena Russian | — | 1415 |
| LMArena Spanish | — | 1448 |
Instruction Following Not comparable
Llama 3.2 90B: —, Qwen3.8 27B: 75.8 (#53)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | — | 1439 |
Long Context Not comparable
Llama 3.2 90B: —, Qwen3.8 27B: 44.3 (#70)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | — | 1450 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Qwen3.8 27B: 65.8 (#43)
| Benchmark | Llama 3.2 90B | Qwen3.8 27B |
|---|---|---|
| LMArena Text | — | 1441 |
| LMArena Creative Writing | — | 1384 |
| EQ-Bench Creative Writing | — | 1671 |
| LMArena Multi-Turn | — | 1441 |
Frequently asked questions
Is Llama 3.2 90B better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Qwen3.8 27B share?
2 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Qwen3.8 27B has 31.