Model comparison
DeepSeek-V3.2-Speciale vs Mercury 2
DeepSeek-V3.2-Speciale and Mercury 2 score almost the same on the Noometry Index (39.7 vs 39.1), so choose on price, context window or the category you care about most.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek-V3.2-Speciale scores higher in 2 categories and Mercury 2 in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.2-Speciale leads 32.9 to 23.8.
- Mercury 2 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.58 / $1.68 for DeepSeek-V3.2-Speciale.
- DeepSeek-V3.2-Speciale has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Speciale | Mercury 2 | |
|---|---|---|
| Provider | DeepSeek | Inception |
| Noometry Index | 39.7 | 39.1 |
| Released | 2025-12-01 | 2026-02-20 |
| Weights | Open | Proprietary |
| Context window | 128K | 128K |
| Max output | 128K | 50K |
| Input $ / M tokens | $0.58 | $0.25 |
| Output $ / M tokens | $1.68 | $0.75 |
| Results tracked | 3 | 17 |
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 2: 33.5 (#255)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury 2 |
|---|---|---|
| WeirdML | 46.7% | 43.2% |
| LMArena WebDev | — | 1171 |
| SciCode | — | 38.7% |
| LMArena Coding | — | 1391 |
| ALE-Bench | — | 785.58 |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.9 (#73), Mercury 2: 23.8 (#170)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury 2 |
|---|---|---|
| SimpleBench | 52.6% | — |
| CritPt | — | 0.8% |
| LMArena Hard Prompts | — | 1362 |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, Mercury 2: 36.2 (#172)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, Mercury 2: 46.6 (#157)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury 2 |
|---|---|---|
| LMArena Non-English | — | 1331 |
| LMArena Chinese | — | 1417 |
| LMArena Russian | — | 1304 |
Instruction Following Not comparable
DeepSeek-V3.2-Speciale: —, Mercury 2: 70.2 (#165)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | — | 1329 |
Long Context Not comparable
DeepSeek-V3.2-Speciale: —, Mercury 2: 40.5 (#154)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury 2 |
|---|---|---|
| LMArena Longer Query | — | 1330 |
Writing & Preference Mercury 2 leads
DeepSeek-V3.2-Speciale: 46.0 (#222), Mercury 2: 53.8 (#155)
| Benchmark | DeepSeek-V3.2-Speciale | Mercury 2 |
|---|---|---|
| LMArena Text | — | 1355 |
| LMArena Creative Writing | — | 1289 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 1358 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Mercury 2?
DeepSeek-V3.2-Speciale and Mercury 2 score almost the same on the Noometry Index (39.7 vs 39.1), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.2-Speciale or Mercury 2?
Mercury 2 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; DeepSeek-V3.2-Speciale lists at $0.58 and $1.68.
Is DeepSeek-V3.2-Speciale or Mercury 2 better for coding?
DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 33.5 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do DeepSeek-V3.2-Speciale and Mercury 2 share?
1 benchmark has published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Mercury 2 has 17.