Model comparison
DeepSeek-V3.2-Speciale vs Step 3
DeepSeek-V3.2-Speciale and Step 3 score almost the same on the Noometry Index (39.1 vs 39.9), so choose on price, context window or the category you care about most.
Last verified . 0 shared benchmarks.
DeepSeek
StepFunSummary
- The widest gap is in writing & preference, where Step 3 leads 54.5 to 46.1.
Side by side
| DeepSeek-V3.2-Speciale | Step 3 | |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 39.1 | 39.9 |
| Released | 2025-12-01 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.58 | — |
| Output $ / M tokens | $1.68 | — |
| Results tracked | 3 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3.2-Speciale: 39.9 (#136), Step 3: 39.5 (#144)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| WeirdML | 46.7% | — |
| LMArena Coding | — | 1367 |
Reasoning DeepSeek-V3.2-Speciale leads
DeepSeek-V3.2-Speciale: 32.1 (#65), Step 3: 27.6 (#102)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| SimpleBench | 52.6% | — |
| Kagi LLM Benchmark | — | 62.3% |
| LMArena Hard Prompts | — | 1355 |
Math Not comparable
DeepSeek-V3.2-Speciale: —, Step 3: 34.9 (#148)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |
Knowledge Not comparable
DeepSeek-V3.2-Speciale: —, Step 3: 36.2 (#161)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Not comparable
DeepSeek-V3.2-Speciale: —, Step 3: 34.9 (#81)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
DeepSeek-V3.2-Speciale: —, Step 3: 46.5 (#154)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |
Instruction Following Not comparable
DeepSeek-V3.2-Speciale: —, Step 3: 70.6 (#159)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
DeepSeek-V3.2-Speciale: —, Step 3: 40.3 (#152)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Step 3 leads
DeepSeek-V3.2-Speciale: 46.1 (#217), Step 3: 54.5 (#146)
| Benchmark | DeepSeek-V3.2-Speciale | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| EQ-Bench Creative Writing | 1276 | — |
| LMArena Multi-Turn | — | 1340 |
Frequently asked questions
Is DeepSeek-V3.2-Speciale better than Step 3?
DeepSeek-V3.2-Speciale and Step 3 score almost the same on the Noometry Index (39.1 vs 39.9), so choose on price, context window or the category you care about most.
Is DeepSeek-V3.2-Speciale or Step 3 better for coding?
They score almost the same on coding (39.9 vs 39.5); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V3.2-Speciale and Step 3 share?
0 benchmarks have published results for both models. DeepSeek-V3.2-Speciale has 3 scored results on Noometry and Step 3 has 17.