Model comparison
DeepSeek-V3.1-Terminus vs Inkling
DeepSeek-V3.1-Terminus and Inkling score almost the same on the Noometry Index (43.1 vs 44.1), so choose on price, context window or the category you care about most.
Last verified . 15 shared benchmarks.
DeepSeekSummary
- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 2 categories and Inkling in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 26.4.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 37.6% for Inkling.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 66K.
Side by side
| DeepSeek-V3.1-Terminus | Inkling | |
|---|---|---|
| Provider | DeepSeek | Thinking Machines Lab |
| Noometry Index | 43.1 | 44.1 |
| Released | 2025-09-22 | 2026-07-15 |
| Weights | Open | Open |
| Context window | 164K | 66K |
| Max output | 147K | 66K |
| Input $ / M tokens | $0.27 | $1.87 |
| Output $ / M tokens | $1 | $4.68 |
| Results tracked | 16 | 41 |
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), Inkling: 34.5 (#234)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| SciCode | 40.6% | 47% |
| LMArena Coding | 1426 | 1464 |
| ALE-Bench | 745.17 | 946 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| WeirdML | — | 32.3% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Inkling: 29.6 (#85)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |
Reasoning Inkling leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Inkling: 40.4 (#56)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| CritPt | 1.7% | 5.4% |
| LMArena Hard Prompts | 1426 | 1451 |
| DTBench | 81.3% | 87.5% |
| LMCA | 28.6% | 37.6% |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| Kagi LLM Benchmark | 57.4% | — |
| ARC-AGI-1 | — | 79.5% |
| Chess Puzzles | — | 21% |
| Epoch Capabilities Index | — | 148.54 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Inkling: 31.3 (#225)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Math | 1402 | 1479 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Inkling: 55.1 (#49)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| LMArena Expert | — | 1465 |
Multilingual Inkling leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Inkling: 54.0 (#52)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Non-English | 1407 | 1434 |
| LMArena Russian | 1436 | 1429 |
| LMArena Chinese | — | 1490 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Spanish | — | 1448 |
Instruction Following Inkling leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Inkling: 75.1 (#71)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Instruction Following | 1404 | 1426 |
Long Context Too close to call
DeepSeek-V3.1-Terminus: 43.4 (#97), Inkling: 43.8 (#86)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Longer Query | 1421 | 1434 |
Writing & Preference Inkling leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Inkling: 65.2 (#51)
| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Text | 1419 | 1441 |
| LMArena Creative Writing | 1403 | 1387 |
| LMArena Multi-Turn | 1411 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Inkling?
DeepSeek-V3.1-Terminus and Inkling score almost the same on the Noometry Index (43.1 vs 44.1), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.1-Terminus or Inkling?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Inkling lists at $1.87 and $4.68.
Is DeepSeek-V3.1-Terminus or Inkling better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
DeepSeek-V3.1-Terminus does, with 164K tokens against 66K.
How many benchmarks do DeepSeek-V3.1-Terminus and Inkling share?
15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Inkling has 41.