# Inkling vs MiMo-V2.6-Pro

> MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 44.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/inkling-vs-mimo-v2-6-pro
- Last updated: 2026-10-11
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Inkling scores higher in 1 category and MiMo-V2.6-Pro in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiMo-V2.6-Pro leads 54.5 to 31.3.
- The biggest single-benchmark swing is ProofBench: 0% for Inkling and 70% for MiMo-V2.6-Pro.
- MiMo-V2.6-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- MiMo-V2.6-Pro accepts more context: 1.05M tokens versus 66K.

## Snapshot

| | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| Provider | Thinking Machines Lab | Xiaomi |
| Noometry Index | 44.1 | 50.3 |
| Rank | 80 | 49 |
| Context | 66K | 1.05M |
| Input $/M | $1.87 | $0.43 |
| Output $/M | $4.68 | $0.87 |
| Weights | Open | Open |

## Coding

- Inkling: 34.5 (#234)
- MiMo-V2.6-Pro: 55.5 (#23)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| LMArena WebDev | 1413 | 1629 |
| SciCode | 47% | 60.9% |
| LMArena Coding | 1464 | 1534 |
| ALE-Bench | 946 | 1,158 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |

## Agentic & Tool Use

- Inkling: 29.6 (#85)
- MiMo-V2.6-Pro: 37.5 (#35)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| APEX-Agents | 33.8% | 59.5% |
| τ²-bench Banking | 25% | — |

## Reasoning

- Inkling: 40.4 (#56)
- MiMo-V2.6-Pro: 43.1 (#50)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| CritPt | 5.4% | 26.6% |
| LMArena Hard Prompts | 1451 | 1512 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |

## Math

- Inkling: 31.3 (#225)
- MiMo-V2.6-Pro: 54.5 (#45)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| ProofBench | 0% | 70% |
| LMArena Math | 1479 | 1494 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |

## Knowledge

- Inkling: 55.1 (#49)
- MiMo-V2.6-Pro: 43.5 (#92)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Expert | 1465 | 1543 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |

## Multimodal

- Inkling: —
- MiMo-V2.6-Pro: 40.8 (#43)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Vision | — | 1264 |

## Multilingual

- Inkling: 54.0 (#52)
- MiMo-V2.6-Pro: 56.9 (#14)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Non-English | 1434 | 1474 |
| LMArena Chinese | 1490 | 1529 |
| LMArena Russian | 1429 | 1480 |
| LMArena French | 1458 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Spanish | 1448 | — |

## Instruction Following

- Inkling: 75.1 (#71)
- MiMo-V2.6-Pro: 78.2 (#12)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Instruction Following | 1426 | 1493 |

## Long Context

- Inkling: 43.8 (#86)
- MiMo-V2.6-Pro: 46.0 (#27)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Longer Query | 1434 | 1501 |

## Writing & Preference

- Inkling: 65.2 (#51)
- MiMo-V2.6-Pro: 66.8 (#33)

| Benchmark | Inkling | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Text | 1441 | 1492 |
| LMArena Creative Writing | 1387 | 1468 |
| LMArena Multi-Turn | 1436 | 1464 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |

## FAQ

### Is Inkling better than MiMo-V2.6-Pro?

MiMo-V2.6-Pro is the stronger model overall, scoring 50.3 to 44.1 on the Noometry Index.

### Which is cheaper, Inkling or MiMo-V2.6-Pro?

MiMo-V2.6-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Inkling lists at $1.87 and $4.68.

### Is Inkling or MiMo-V2.6-Pro better for coding?

MiMo-V2.6-Pro scores higher on coding benchmarks: 55.5 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.6-Pro does, with 1.05M tokens against 66K.

### How many benchmarks do Inkling and MiMo-V2.6-Pro share?

18 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and MiMo-V2.6-Pro has 19.