Model comparison
DeepSeek-V3.2-Speciale vs Llama 3.2 90B
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 27.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
MetaSummary
- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.1 to 20.9.
Side by side
| DeepSeek-V3.2-Speciale | Llama 3.2 90B | |
|---|---|---|
| Provider | DeepSeek | Meta |
| Noometry Index | 39.1 | 27.1 |
| Released | 2025-12-01 | 2024-09-24 |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.58 | — |
| Output $ / M tokens | $1.68 | — |
| Results tracked | 3 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V3.2-Speciale: 39.9 (#136), Llama 3.2 90B: —
| Benchmark | DeepSeek-V3.2-Speciale | Llama 3.2 90B |
|---|---|---|
| WeirdML | 46.7% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Speciale: —, Llama 3.2 90B: 29.7 (#73)
| Benchmark | DeepSeek-V3.2-Speciale | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.1 (#65), Llama 3.2 90B: 20.9 (#207)
| Benchmark | DeepSeek-V3.2-Speciale | Llama 3.2 90B |
|---|---|---|
| SimpleBench | 52.6% | — |
| EnigmaEval | — | 0.4% |
| Epoch Capabilities Index | — | 125.5 |
Math Not comparable
DeepSeek-V3.2-Speciale: —, Llama 3.2 90B: 10.4 (#302)
| Benchmark | DeepSeek-V3.2-Speciale | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| MATH Level 5 | — | 39.4% |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, Llama 3.2 90B: 21.7 (#269)
| Benchmark | DeepSeek-V3.2-Speciale | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| MMLU | — | 80.3% |
Multimodal Not comparable
DeepSeek-V3.2-Speciale: —, Llama 3.2 90B: 24.9 (#119)
| Benchmark | DeepSeek-V3.2-Speciale | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Writing & Preference Not comparable
DeepSeek-V3.2-Speciale: 46.1 (#217), Llama 3.2 90B: —
| Benchmark | DeepSeek-V3.2-Speciale | Llama 3.2 90B |
|---|---|---|
| EQ-Bench Creative Writing | 1276 | — |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Llama 3.2 90B?
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 27.1 on the Noometry Index.
How many benchmarks do DeepSeek-V3.2-Speciale and Llama 3.2 90B share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Llama 3.2 90B has 9.