Model comparison
DeepSeek-V3.2-Speciale vs Mercury
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 37.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.9 to 17.5.
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Speciale | Mercury | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 39.7 | 37.6 |
| 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 | 9 |
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: 40.4 (#140), Mercury: 38.7 (#170)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury |
|---|---|---|
| WeirdML | 46.7% | — |
| LMArena Coding | — | 1322 |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.9 (#73), Mercury: 17.5 (#293)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury |
|---|---|---|
| SimpleBench | 52.6% | — |
| Kagi LLM Benchmark | — | 21.6% |
| LMArena Hard Prompts | — | 1285 |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, Mercury: 41.6 (#206)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury |
|---|---|---|
| LMArena Non-English | — | 1260 |
Instruction Following Not comparable
DeepSeek-V3.2-Speciale: —, Mercury: 65.2 (#224)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury |
|---|---|---|
| LMArena Instruction Following | — | 1239 |
Long Context Not comparable
DeepSeek-V3.2-Speciale: —, Mercury: 38.4 (#198)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury |
|---|---|---|
| LMArena Longer Query | — | 1266 |
Writing & Preference Too close to call
DeepSeek-V3.2-Speciale: 46.0 (#222), Mercury: 46.2 (#221)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury |
|---|---|---|
| LMArena Text | — | 1282 |
| LMArena Creative Writing | — | 1191 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 1282 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Mercury?
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 37.6 on the Noometry Index.
Is DeepSeek-V3.2-Speciale or Mercury better for coding?
DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 38.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Speciale and Mercury share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Mercury has 9.