Model comparison
Llama 3.2 90B vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 27.5 on the Noometry Index.
Last verified . 3 shared benchmarks.
Meta
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Llama 3.2 90B scores higher in 0 categories and Qwen3.6 Max Preview in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 54.1 to 11.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 91.1% for Qwen3.6 Max Preview.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 90B | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.5 | 51.5 |
| Released | 2024-09-24 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.30 |
| Output $ / M tokens | — | $7.80 |
| Results tracked | 9 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |
| LMArena Coding | — | 1471 |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 30.0 (#80), Qwen3.6 Max Preview: —
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| BALROG | 27.3% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
Llama 3.2 90B: 21.7 (#217), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 149.24 |
| SimpleBench | — | 63% |
| NYT Connections (extended) | — | 74.1% |
| Chess Puzzles | — | 20% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1457 |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
Math Qwen3.6 Max Preview leads
Llama 3.2 90B: 11.1 (#308), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 91.1% |
| LMArena Math | — | 1465 |
| MATH Level 5 | 39.4% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Llama 3.2 90B: 21.7 (#274), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 41% | 87.4% |
| SimpleQA Verified | — | 52% |
| LMArena Expert | — | 1478 |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 25.4 (#124), Qwen3.6 Max Preview: —
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | — | 1437 |
| LMArena Chinese | — | 1487 |
| LMArena French | — | 1449 |
| LMArena Russian | — | 1445 |
| LMArena Spanish | — | 1454 |
Instruction Following Not comparable
Llama 3.2 90B: —, Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | — | 1438 |
Long Context Not comparable
Llama 3.2 90B: —, Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | — | 1457 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Llama 3.2 90B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | — | 1447 |
| LMArena Creative Writing | — | 1435 |
| LMArena Multi-Turn | — | 1456 |
Frequently asked questions
Is Llama 3.2 90B better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Qwen3.6 Max Preview share?
3 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Qwen3.6 Max Preview has 29.