Model comparison
Llama 3.2 90B vs Qwen3-30B-A3B
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 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 1 category and Qwen3-30B-A3B in 3 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3-30B-A3B 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 70.3% for Qwen3-30B-A3B.
Side by side
| Llama 3.2 90B | Qwen3-30B-A3B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.5 | 38.9 |
| Released | 2024-09-24 | 2025-04-28 |
| Weights | Open | Open |
| Context window | — | 41K |
| Max output | — | 16K |
| Input $ / M tokens | — | $0.12 |
| Output $ / M tokens | — | $0.50 |
| 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: —, Qwen3-30B-A3B: 37.5 (#194)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| SciCode | — | 33.3% |
| WeirdML | — | 29.8% |
| LMArena Coding | — | 1416 |
Agentic & Tool Use Too close to call
Llama 3.2 90B: 30.0 (#80), Qwen3-30B-A3B: 29.8 (#82)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41.4% |
| BALROG | 27.3% | — |
Reasoning Too close to call
Llama 3.2 90B: 21.7 (#217), Qwen3-30B-A3B: 22.2 (#204)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 139.63 |
| Kagi LLM Benchmark | — | 54.9% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 8% |
| EnigmaEval | 0.4% | — |
| LMArena Hard Prompts | — | 1398 |
| DTBench | — | 69.3% |
| LMCA | — | 22.4% |
Math Qwen3-30B-A3B leads
Llama 3.2 90B: 11.1 (#308), Qwen3-30B-A3B: 37.4 (#157)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 70.3% |
| MathArena Final-Answer Competitions | — | 47.8% |
| LMArena Math | — | 1394 |
| MATH Level 5 | 39.4% | — |
Knowledge Qwen3-30B-A3B leads
Llama 3.2 90B: 21.7 (#274), Qwen3-30B-A3B: 41.8 (#105)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| GPQA Diamond | 41% | 70.1% |
| Confabulations | — | 12.3% |
| LMArena Expert | — | 1396 |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 25.4 (#124), Qwen3-30B-A3B: —
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Multilingual Not comparable
Llama 3.2 90B: —, Qwen3-30B-A3B: 49.5 (#132)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Non-English | — | 1372 |
| LMArena Chinese | — | 1433 |
| LMArena French | — | 1418 |
| LMArena German | — | 1380 |
| LMArena Japanese | — | 1337 |
| LMArena Korean | — | 1331 |
| LMArena Russian | — | 1370 |
| LMArena Spanish | — | 1404 |
Instruction Following Not comparable
Llama 3.2 90B: —, Qwen3-30B-A3B: 72.0 (#142)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Instruction Following | — | 1363 |
Long Context Not comparable
Llama 3.2 90B: —, Qwen3-30B-A3B: 31.0 (#283)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| Fiction.LiveBench | — | 40.6% |
| LMArena Longer Query | — | 1379 |
Writing & Preference Not comparable
Llama 3.2 90B: —, Qwen3-30B-A3B: 55.6 (#143)
| Benchmark | Llama 3.2 90B | Qwen3-30B-A3B |
|---|---|---|
| LMArena Text | — | 1384 |
| LMArena Creative Writing | — | 1317 |
| Short-Story Creative Writing | — | 75.3% |
| LMArena Multi-Turn | — | 1378 |
Frequently asked questions
Is Llama 3.2 90B better than Qwen3-30B-A3B?
Qwen3-30B-A3B is the stronger model overall, scoring 38.9 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Qwen3-30B-A3B share?
3 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Qwen3-30B-A3B has 32.