Model comparison
DeepSeek-V3.1 vs DeepSeek-V3.1-Terminus
DeepSeek-V3.1 and DeepSeek-V3.1-Terminus score almost the same on the Noometry Index (42.8 vs 43.1), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
DeepSeekSummary
- They share 13 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 2 categories and DeepSeek-V3.1-Terminus in 5 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in long context, where DeepSeek-V3.1-Terminus leads 43.4 to 36.3.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $0.27 / $1 for DeepSeek-V3.1-Terminus.
Side by side
| DeepSeek-V3.1 | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 42.8 | 43.1 |
| Released | 2025-08-21 | 2025-09-22 |
| Weights | Open | Open |
| Context window | 164K | 164K |
| Max output | 8K | 147K |
| Input $ / M tokens | $0.25 | $0.27 |
| Output $ / M tokens | $0.95 | $1 |
| Results tracked | 27 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1: 40.3 (#144), DeepSeek-V3.1-Terminus: 42.0 (#113)
| Benchmark | DeepSeek-V3.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1417 | 1426 |
| SciCode | — | 40.6% |
| WeirdML | 38.4% | — |
| ALE-Bench | — | 745.17 |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), DeepSeek-V3.1-Terminus: 26.4 (#133)
| Benchmark | DeepSeek-V3.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 57.4% |
| LMArena Hard Prompts | 1417 | 1426 |
| DTBench | 82.7% | 81.3% |
| LMCA | 24.3% | 28.6% |
| SimpleBench | 40% | — |
| CritPt | — | 1.7% |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Too close to call
DeepSeek-V3.1: 38.9 (#122), DeepSeek-V3.1-Terminus: 38.5 (#137)
| Benchmark | DeepSeek-V3.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1420 | 1402 |
Knowledge Not comparable
DeepSeek-V3.1: 43.7 (#90), DeepSeek-V3.1-Terminus: —
| Benchmark | DeepSeek-V3.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |
Multilingual Too close to call
DeepSeek-V3.1: 51.6 (#106), DeepSeek-V3.1-Terminus: 52.1 (#92)
| Benchmark | DeepSeek-V3.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1400 | 1407 |
| LMArena Russian | 1405 | 1436 |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Too close to call
DeepSeek-V3.1: 73.9 (#110), DeepSeek-V3.1-Terminus: 74.0 (#106)
| Benchmark | DeepSeek-V3.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1400 | 1404 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1: 36.3 (#232), DeepSeek-V3.1-Terminus: 43.4 (#97)
| Benchmark | DeepSeek-V3.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1422 | 1421 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference Too close to call
DeepSeek-V3.1: 60.3 (#98), DeepSeek-V3.1-Terminus: 61.0 (#92)
| Benchmark | DeepSeek-V3.1 | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1420 | 1419 |
| LMArena Creative Writing | 1401 | 1403 |
| LMArena Multi-Turn | 1408 | 1411 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than DeepSeek-V3.1-Terminus?
DeepSeek-V3.1 and DeepSeek-V3.1-Terminus score almost the same on the Noometry Index (42.8 vs 43.1), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1 or DeepSeek-V3.1-Terminus?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; DeepSeek-V3.1-Terminus lists at $0.27 and $1.
Is DeepSeek-V3.1 or DeepSeek-V3.1-Terminus better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 40.3 in the Noometry coding category.
Which has the bigger context window?
Both accept 164K tokens.
How many benchmarks do DeepSeek-V3.1 and DeepSeek-V3.1-Terminus share?
13 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.