Model comparison
DeepSeek-V3.1-Terminus vs Step 3
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 39.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeek
StepFunSummary
- They share 11 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 6 categories and Step 3 in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 54.5.
Side by side
| DeepSeek-V3.1-Terminus | Step 3 | |
|---|---|---|
| Provider | DeepSeek | StepFun |
| Noometry Index | 42.6 | 39.9 |
| Released | 2025-09-22 | — |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 17 |
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: 41.5 (#114), Step 3: 39.5 (#144)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| LMArena Coding | 1426 | 1367 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning Step 3 leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Step 3: 27.6 (#102)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 62.3% |
| LMArena Hard Prompts | 1427 | 1355 |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
Math Too close to call
DeepSeek-V3.1-Terminus: 35.7 (#138), Step 3: 34.9 (#148)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| LMArena Math | 1402 | 1366 |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Step 3: 36.2 (#161)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Step 3: 34.9 (#81)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Step 3: 46.5 (#154)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| LMArena Non-English | 1407 | 1327 |
| LMArena Russian | 1434 | 1331 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Spanish | — | 1372 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Step 3: 70.6 (#159)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1332 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Step 3: 40.3 (#152)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| LMArena Longer Query | 1426 | 1326 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Step 3: 54.5 (#146)
| Benchmark | DeepSeek-V3.1-Terminus | Step 3 |
|---|---|---|
| LMArena Text | 1420 | 1351 |
| LMArena Creative Writing | 1404 | 1322 |
| LMArena Multi-Turn | 1411 | 1340 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Step 3?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 39.9 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Step 3 better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 39.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Step 3 share?
11 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Step 3 has 17.