# Inkling vs MiMo-V2-Pro

> Inkling is the stronger model overall, scoring 44.1 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 4.7× 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/inkling-vs-mimo-v2-pro
- Last updated: 2026-10-12
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Inkling scores higher in 5 categories and MiMo-V2-Pro in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 22.1.
- MiMo-V2-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- MiMo-V2-Pro accepts more context: 1.05M tokens versus 66K.
- Inkling has downloadable open weights; the other is API-only.

## Snapshot

| | Inkling | MiMo-V2-Pro |
|---|---|---|
| Provider | Thinking Machines Lab | Xiaomi |
| Noometry Index | 44.1 | 43.0 |
| Rank | 80 | 103 |
| Context | 66K | 1.05M |
| Input $/M | $1.87 | $0.43 |
| Output $/M | $4.68 | $0.87 |
| Weights | Open | Proprietary |

## Coding

- Inkling: 34.5 (#234)
- MiMo-V2-Pro: 43.8 (#83)

| Benchmark | Inkling | MiMo-V2-Pro |
|---|---|---|
| LMArena WebDev | 1413 | 1433 |
| LMArena Coding | 1464 | 1476 |
| ALE-Bench | 946 | 785.17 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |

## Agentic & Tool Use

- Inkling: 29.6 (#85)
- MiMo-V2-Pro: —

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

## Reasoning

- Inkling: 40.4 (#56)
- MiMo-V2-Pro: 22.1 (#206)

| Benchmark | Inkling | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1457 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| NYT Connections (extended) | — | 25.8% |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| Thematic Generalization | — | 45.9% |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |

## Math

- Inkling: 31.3 (#225)
- MiMo-V2-Pro: 39.5 (#102)

| Benchmark | Inkling | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1479 | 1447 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |

## Knowledge

- Inkling: 55.1 (#49)
- MiMo-V2-Pro: 41.4 (#111)

| Benchmark | Inkling | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1465 | 1478 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |

## Multilingual

- Inkling: 54.0 (#52)
- MiMo-V2-Pro: 52.7 (#81)

| Benchmark | Inkling | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1434 | 1416 |
| LMArena Chinese | 1490 | 1456 |
| LMArena French | 1458 | 1469 |
| LMArena German | 1446 | 1417 |
| LMArena Japanese | 1429 | 1366 |
| LMArena Korean | 1404 | 1400 |
| LMArena Russian | 1429 | 1427 |
| LMArena Spanish | 1448 | 1457 |

## Instruction Following

- Inkling: 75.1 (#71)
- MiMo-V2-Pro: 76.0 (#49)

| Benchmark | Inkling | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1426 | 1445 |

## Long Context

- Inkling: 43.8 (#86)
- MiMo-V2-Pro: 41.5 (#138)

| Benchmark | Inkling | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1434 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |

## Writing & Preference

- Inkling: 65.2 (#51)
- MiMo-V2-Pro: 62.8 (#70)

| Benchmark | Inkling | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1441 | 1436 |
| LMArena Creative Writing | 1387 | 1415 |
| LMArena Multi-Turn | 1436 | 1456 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |

## FAQ

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

Inkling is the stronger model overall, scoring 44.1 to 43.0 on the Noometry Index. MiMo-V2-Pro costs 4.7× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

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

MiMo-V2-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-Pro better for coding?

MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 34.5 in the Noometry coding category.

### Which has the bigger context window?

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

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

19 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and MiMo-V2-Pro has 23.