# DeepSeek-V3.1-Terminus vs Inkling

> Inkling is the stronger model overall, scoring 44.1 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 5.4× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-inkling
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 2 categories and Inkling in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 25.7.
- 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 $0.30 / $1 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- DeepSeek-V3.1-Terminus accepts more context: 164K tokens versus 66K.

## Snapshot

| | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| Provider | DeepSeek | Thinking Machines Lab |
| Noometry Index | 42.6 | 44.1 |
| Rank | 96 | 75 |
| Context | 164K | 66K |
| Input $/M | $0.30 | $1.87 |
| Output $/M | $1 | $4.68 |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 41.5 (#114)
- Inkling: 34.1 (#229)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| SciCode | 40.6% | 47% |
| LMArena Coding | 1426 | 1463 |
| ALE-Bench | 745.17 | 946 |
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1412 |
| FrontierSWE | — | 4.1% |
| WeirdML | — | 32.3% |

## Agentic & Tool Use

- DeepSeek-V3.1-Terminus: —
- Inkling: 29.5 (#76)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |

## Reasoning

- DeepSeek-V3.1-Terminus: 25.7 (#126)
- Inkling: 40.6 (#48)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| CritPt | 1.7% | 5.4% |
| LMArena Hard Prompts | 1427 | 1452 |
| 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 | — | 148.6 |

## Math

- DeepSeek-V3.1-Terminus: 35.7 (#138)
- Inkling: 31.2 (#198)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Math | 1402 | 1482 |
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Inkling: 55.2 (#44)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| LMArena Expert | — | 1468 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.3 (#87)
- Inkling: 54.2 (#49)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Non-English | 1407 | 1434 |
| LMArena Russian | 1434 | 1430 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1453 |
| LMArena German | — | 1456 |
| LMArena Japanese | — | 1428 |
| LMArena Korean | — | 1401 |
| LMArena Spanish | — | 1442 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.4 (#96)
- Inkling: 75.3 (#65)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Instruction Following | 1406 | 1427 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.5 (#88)
- Inkling: 43.9 (#79)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Longer Query | 1426 | 1436 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.3 (#87)
- Inkling: 65.5 (#48)

| Benchmark | DeepSeek-V3.1-Terminus | Inkling |
|---|---|---|
| LMArena Text | 1420 | 1443 |
| LMArena Creative Writing | 1404 | 1390 |
| LMArena Multi-Turn | 1411 | 1436 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 5.4× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

### Which is cheaper, DeepSeek-V3.1-Terminus or Inkling?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 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: 41.5 versus 34.1 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.