Model comparison
Llama 3.2 90B vs Qwen3 8B
Qwen3 8B is the stronger model overall, scoring 33.3 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 1 category and Qwen3 8B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 8B leads 33.3 to 10.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.6% for Llama 3.2 90B and 56.1% for Qwen3 8B.
Side by side
| Llama 3.2 90B | Qwen3 8B | |
|---|---|---|
| Provider | Meta | Alibaba (Qwen) |
| Noometry Index | 27.1 | 33.3 |
| Released | 2024-09-24 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.18 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 9 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.2 90B: —, Qwen3 8B: 33.4 (#245)
| Benchmark | Llama 3.2 90B | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |
Agentic & Tool Use Too close to call
Llama 3.2 90B: 29.7 (#73), Qwen3 8B: 29.9 (#71)
| Benchmark | Llama 3.2 90B | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |
| BALROG | 27.3% | — |
Reasoning Llama 3.2 90B leads
Llama 3.2 90B: 20.9 (#207), Qwen3 8B: 16.1 (#299)
| Benchmark | Llama 3.2 90B | Qwen3 8B |
|---|---|---|
| Epoch Capabilities Index | 125.5 | 136.17 |
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| EnigmaEval | 0.4% | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
Math Qwen3 8B leads
Llama 3.2 90B: 10.4 (#302), Qwen3 8B: 33.3 (#176)
| Benchmark | Llama 3.2 90B | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.6% | 56.1% |
| MATH Level 5 | 39.4% | — |
Knowledge Qwen3 8B leads
Llama 3.2 90B: 21.7 (#269), Qwen3 8B: 36.1 (#164)
| Benchmark | Llama 3.2 90B | Qwen3 8B |
|---|---|---|
| GPQA Diamond | 41% | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
| MMLU | 80.3% | — |
Multimodal Not comparable
Llama 3.2 90B: 24.9 (#119), Qwen3 8B: —
| Benchmark | Llama 3.2 90B | Qwen3 8B |
|---|---|---|
| LMArena Vision | 1000 | — |
| GeoBench | 52% | — |
Long Context Not comparable
Llama 3.2 90B: —, Qwen3 8B: 37.8 (#205)
| Benchmark | Llama 3.2 90B | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
Frequently asked questions
Is Llama 3.2 90B better than Qwen3 8B?
Qwen3 8B is the stronger model overall, scoring 33.3 to 27.1 on the Noometry Index.
How many benchmarks do Llama 3.2 90B and Qwen3 8B share?
3 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Qwen3 8B has 11.