Model comparison
DeepSeek-V3.2-Speciale vs Hunyuan Large 2025 02 10
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 38.0 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
TencentSummary
- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.1 to 24.5.
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 | |
|---|---|---|
| Provider | DeepSeek | Tencent |
| Noometry Index | 39.1 | 38.0 |
| Released | 2025-12-01 | — |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.58 | — |
| Output $ / M tokens | $1.68 | — |
| Results tracked | 3 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 39.9 (#136), Hunyuan Large 2025 02 10: 37.6 (#177)
| Benchmark | DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 |
|---|---|---|
| WeirdML | 46.7% | — |
| LMArena Coding | — | 1307 |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.1 (#65), Hunyuan Large 2025 02 10: 24.5 (#147)
| Benchmark | DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 |
|---|---|---|
| SimpleBench | 52.6% | — |
| LMArena Hard Prompts | — | 1286 |
Math Not comparable
DeepSeek-V3.2-Speciale: —, Hunyuan Large 2025 02 10: 33.1 (#178)
| Benchmark | DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Math | — | 1281 |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, Hunyuan Large 2025 02 10: 34.5 (#188)
| Benchmark | DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Expert | — | 1276 |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, Hunyuan Large 2025 02 10: 42.1 (#195)
| Benchmark | DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Non-English | — | 1265 |
| LMArena Chinese | — | 1346 |
| LMArena Russian | — | 1266 |
Instruction Following Not comparable
DeepSeek-V3.2-Speciale: —, Hunyuan Large 2025 02 10: 67.6 (#192)
| Benchmark | DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Instruction Following | — | 1277 |
Long Context Not comparable
DeepSeek-V3.2-Speciale: —, Hunyuan Large 2025 02 10: 40.8 (#144)
| Benchmark | DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Longer Query | — | 1342 |
Writing & Preference Hunyuan Large 2025 02 10 leads
DeepSeek-V3.2-Speciale: 46.1 (#217), Hunyuan Large 2025 02 10: 48.9 (#191)
| Benchmark | DeepSeek-V3.2-Speciale | Hunyuan Large 2025 02 10 |
|---|---|---|
| LMArena Text | — | 1288 |
| LMArena Creative Writing | — | 1264 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 1284 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Hunyuan Large 2025 02 10?
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.1 to 38.0 on the Noometry Index.
Is DeepSeek-V3.2-Speciale or Hunyuan Large 2025 02 10 better for coding?
DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 39.9 versus 37.6 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Speciale and Hunyuan Large 2025 02 10 share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Hunyuan Large 2025 02 10 has 12.