Model comparison
Llama 3.2 90B vs Qwen3 14B
Qwen3 14B is the stronger model overall, scoring 35.0 to 27.1 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 2 categories and Qwen3 14B in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 14B leads 37.0 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 66.4% for Qwen3 14B.
Side by side
| Llama 3.2 90B | Qwen3 14B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.1 | 35.0 |
| Released | 2024-09-24 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $1.40 |
| Results tracked | 9 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Qwen3 14B: 36.7 (#191)
| Benchmark | Llama 3.2 90B | Qwen3 14B |
|---|---|---|
| SciCode | — | 31.6% |
Agentic & Tool Use Too close to call
Llama 3.2 90B: 29.7 (#73), Qwen3 14B: 29.4 (#78)
| Benchmark | Llama 3.2 90B | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |
| BALROG | 27.3% | — |
Reasoning Llama 3.2 90B leads
Llama 3.2 90B: 20.9 (#207), Qwen3 14B: 18.1 (#272)
| Benchmark | Llama 3.2 90B | Qwen3 14B |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 138.23 |
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| Chess Puzzles | — | 4% |
| EnigmaEval | 0.4% | — |
| DTBench | — | 64% |
| LMCA | — | 18.2% |
Math Qwen3 14B leads
Llama 3.2 90B: 10.4 (#302), Qwen3 14B: 37.0 (#102)
| Benchmark | Llama 3.2 90B | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 66.4% |
| MATH Level 5 | 39.4% | — |
Knowledge Qwen3 14B leads
Llama 3.2 90B: 21.7 (#269), Qwen3 14B: 39.2 (#124)
| Benchmark | Llama 3.2 90B | Qwen3 14B |
|---|---|---|
| GPQA Diamond | 41% | 63.8% |
| Vectara Hallucination Rate | — | 5.4% |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 24.9 (#119), Qwen3 14B: —
| Benchmark | Llama 3.2 90B | Qwen3 14B |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Long Context Not comparable
Llama 3.2 90B: —, Qwen3 14B: 38.0 (#201)
| Benchmark | Llama 3.2 90B | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
Frequently asked questions
Is Llama 3.2 90B better than Qwen3 14B?
Qwen3 14B is the stronger model overall, scoring 35.0 to 27.1 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Qwen3 14B share?
3 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Qwen3 14B has 12.