Model comparison
Llama 3.2 90B vs Qwen3.5-Flash
Qwen3.5-Flash is the stronger model overall, scoring 42.5 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 Qwen3.5-Flash in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5-Flash leads 37.4 to 11.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 84.4% for Qwen3.5-Flash.
- Llama 3.2 90B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 90B | Qwen3.5-Flash | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.5 | 42.5 |
| Released | 2024-09-24 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 9 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Qwen3.5-Flash: 34.2 (#242)
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | — | 1244 |
| LMArena Coding | — | 1412 |
| ALE-Bench | — | 221.8 |
Agentic & Tool Use Not comparable
Llama 3.2 90B: 30.0 (#80), Qwen3.5-Flash: —
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| BALROG | 27.3% | — |
| Vending-Bench 2 | — | 462.69 |
Reasoning Qwen3.5-Flash leads
Llama 3.2 90B: 21.7 (#217), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 143.98 |
| Chess Puzzles | — | 21% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1403 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 82.9% |
| LMCA | — | 29.1% |
Math Qwen3.5-Flash leads
Llama 3.2 90B: 11.1 (#308), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 84.4% |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| LMArena Math | — | 1407 |
| MATH Level 5 | 39.4% | — |
| FrontierMath (Feb 2025 set) | — | 6.2% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3.5-Flash leads
Llama 3.2 90B: 21.7 (#274), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 41% | 82.3% |
| SimpleQA Verified | — | 20.3% |
| Vectara Hallucination Rate | — | 10.5% |
| LMArena Expert | — | 1407 |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 25.4 (#124), Qwen3.5-Flash: —
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Qwen3.5-Flash: 50.5 (#121)
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | — | 1385 |
| LMArena Chinese | — | 1446 |
| LMArena French | — | 1412 |
| LMArena German | — | 1390 |
| LMArena Japanese | — | 1368 |
| LMArena Korean | — | 1344 |
| LMArena Russian | — | 1379 |
| LMArena Spanish | — | 1400 |
Instruction Following Not comparable
Llama 3.2 90B: —, Qwen3.5-Flash: 72.6 (#139)
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | — | 1374 |
Long Context Not comparable
Llama 3.2 90B: —, Qwen3.5-Flash: 42.4 (#124)
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | — | 1392 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Qwen3.5-Flash: 57.9 (#122)
| Benchmark | Llama 3.2 90B | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | — | 1397 |
| LMArena Creative Writing | — | 1343 |
| LMArena Multi-Turn | — | 1393 |
Frequently asked questions
Is Llama 3.2 90B better than Qwen3.5-Flash?
Qwen3.5-Flash is the stronger model overall, scoring 42.5 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Qwen3.5-Flash share?
3 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Qwen3.5-Flash has 32.