Model comparison
DeepSeek-V3.1-Terminus vs DeepSeek-V3.2-Speciale
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 39.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 46.0.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $0.58 / $1.68 for DeepSeek-V3.2-Speciale.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 128K.
Side by side
| DeepSeek-V3.1-Terminus | DeepSeek-V3.2-Speciale | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 43.1 | 39.7 |
| Released | 2025-09-22 | 2025-12-01 |
| Weights | Open | Open |
| Context window | 164K | 128K |
| Max output | 147K | 128K |
| Input $ / M tokens | $0.27 | $0.58 |
| Output $ / M tokens | $1 | $1.68 |
| Results tracked | 16 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 42.0 (#113), DeepSeek-V3.2-Speciale: 40.4 (#140)
| Benchmark | DeepSeek-V3.1-Terminus | DeepSeek-V3.2-Speciale |
|---|---|---|
| SciCode | 40.6% | — |
| WeirdML | — | 46.7% |
| LMArena Coding | 1426 | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.1-Terminus: 26.4 (#133), DeepSeek-V3.2-Speciale: 32.9 (#73)
| Benchmark | DeepSeek-V3.1-Terminus | DeepSeek-V3.2-Speciale |
|---|---|---|
| SimpleBench | — | 52.6% |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| LMArena Hard Prompts | 1426 | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Not comparable
DeepSeek-V3.1-Terminus: 38.5 (#137), DeepSeek-V3.2-Speciale: —
| Benchmark | DeepSeek-V3.1-Terminus | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Math | 1402 | — |
Multilingual Not comparable
DeepSeek-V3.1-Terminus: 52.1 (#92), DeepSeek-V3.2-Speciale: —
| Benchmark | DeepSeek-V3.1-Terminus | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Non-English | 1407 | — |
| LMArena Russian | 1436 | — |
Instruction Following Not comparable
DeepSeek-V3.1-Terminus: 74.0 (#106), DeepSeek-V3.2-Speciale: —
| Benchmark | DeepSeek-V3.1-Terminus | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Instruction Following | 1404 | — |
Long Context Not comparable
DeepSeek-V3.1-Terminus: 43.4 (#97), DeepSeek-V3.2-Speciale: —
| Benchmark | DeepSeek-V3.1-Terminus | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Longer Query | 1421 | — |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), DeepSeek-V3.2-Speciale: 46.0 (#222)
| Benchmark | DeepSeek-V3.1-Terminus | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Text | 1419 | — |
| LMArena Creative Writing | 1403 | — |
| EQ-Bench Creative Writing | — | 1276 |
| LMArena Multi-Turn | 1411 | — |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than DeepSeek-V3.2-Speciale?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 39.7 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or DeepSeek-V3.2-Speciale?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; DeepSeek-V3.2-Speciale lists at $0.58 and $1.68.
Is DeepSeek-V3.1-Terminus or DeepSeek-V3.2-Speciale better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 40.4 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 128K.
How many benchmarks do DeepSeek-V3.1-Terminus and DeepSeek-V3.2-Speciale share?
0 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.