# Kimi K2.6 vs MiMo-V2.5-Pro

> Kimi K2.6 is the stronger model overall, scoring 47.5 to 44.8 on the Noometry Index. MiMo-V2.5-Pro costs 3.1× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/kimi-k2-6-vs-mimo-v2-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. Kimi K2.6 scores higher in 5 categories and MiMo-V2.5-Pro in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 56.8 to 38.6.
- The biggest single-benchmark swing is NYT Connections (extended): 87.2% for Kimi K2.6 and 34.4% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| Provider | Moonshot AI | Xiaomi |
| Noometry Index | 47.5 | 44.8 |
| Rank | 52 | 70 |
| Context | 262K | 1.05M |
| Input $/M | $0.95 | $0.43 |
| Output $/M | $4 | $0.87 |
| Weights | Open | Open |

## Coding

- Kimi K2.6: 50.5 (#41)
- MiMo-V2.5-Pro: 47.0 (#58)

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1509 | 1477 |
| SciCode | 53.5% | 50.2% |
| LMArena Coding | 1488 | 1502 |
| ALE-Bench | 1,093 | 899.8 |
| SWE-bench Verified | 76.7% | — |
| WeirdML | 55.9% | — |

## Agentic & Tool Use

- Kimi K2.6: 21.8 (#128)
- MiMo-V2.5-Pro: —

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| OSWorld 2.0 | 4.6% | — |
| ExploitBench | 18.4% | — |
| GBAEval | 0.9% | — |
| GDP.pdf | 12% | — |
| Vending-Bench 2 | 6,205 | — |

## Reasoning

- Kimi K2.6: 39.6 (#51)
- MiMo-V2.5-Pro: 25.9 (#124)

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| NYT Connections (extended) | 87.2% | 34.4% |
| CritPt | 8% | 4% |
| LMArena Hard Prompts | 1470 | 1487 |
| DTBench | 90.9% | 84.5% |
| LMCA | 37.3% | 29.5% |
| Chess Puzzles | 26% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 18% | — |
| Epoch Capabilities Index | 151.03 | — |

## Math

- Kimi K2.6: 56.8 (#34)
- MiMo-V2.5-Pro: 38.6 (#84)

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 16% | 22% |
| LMArena Math | 1475 | 1480 |
| FrontierMath (Tiers 1-3) | 57.2% | — |
| FrontierMath Tier 4 | 25.6% | — |
| MathArena Final-Answer Competitions | 72.9% | — |
| OTIS Mock AIME 2024-2025 | 96.1% | — |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |

## Knowledge

- Kimi K2.6: 53.9 (#48)
- MiMo-V2.5-Pro: 41.5 (#100)

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1491 | 1501 |
| GPQA Diamond | 90.8% | — |
| SimpleQA Verified | 34.9% | — |
| Vectara Hallucination Rate | 10.8% | — |

## Multimodal

- Kimi K2.6: 31.8 (#95)
- MiMo-V2.5-Pro: —

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Vision | 1282 | — |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |

## Multilingual

- Kimi K2.6: 55.1 (#35)
- MiMo-V2.5-Pro: 55.3 (#33)

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1446 | 1449 |
| LMArena Chinese | 1521 | 1507 |
| LMArena French | 1471 | 1489 |
| LMArena German | 1449 | 1455 |
| LMArena Japanese | 1442 | 1418 |
| LMArena Korean | 1428 | 1436 |
| LMArena Russian | 1446 | 1450 |
| LMArena Spanish | 1463 | 1470 |

## Instruction Following

- Kimi K2.6: 76.5 (#40)
- MiMo-V2.5-Pro: 77.6 (#21)

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1451 | 1477 |

## Long Context

- Kimi K2.6: 44.9 (#50)
- MiMo-V2.5-Pro: 45.4 (#38)

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1468 | 1482 |

## Writing & Preference

- Kimi K2.6: 68.7 (#25)
- MiMo-V2.5-Pro: 65.5 (#47)

| Benchmark | Kimi K2.6 | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1455 | 1465 |
| LMArena Creative Writing | 1434 | 1440 |
| EQ-Bench Creative Writing | 1725 | 1493 |
| EQ-Bench 4 | 1202 | 1208 |
| LMArena Multi-Turn | 1453 | 1477 |

## FAQ

### Is Kimi K2.6 better than MiMo-V2.5-Pro?

Kimi K2.6 is the stronger model overall, scoring 47.5 to 44.8 on the Noometry Index. MiMo-V2.5-Pro costs 3.1× less per token, which makes it the better buy when Kimi K2.6's lead doesn't matter for your workload.

### Which is cheaper, Kimi K2.6 or MiMo-V2.5-Pro?

MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Kimi K2.6 lists at $0.95 and $4.

### Is Kimi K2.6 or MiMo-V2.5-Pro better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 47.0 in the Noometry coding category.

### Which has the bigger context window?

MiMo-V2.5-Pro does, with 1.05M tokens against 262K.

### How many benchmarks do Kimi K2.6 and MiMo-V2.5-Pro share?

27 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and MiMo-V2.5-Pro has 27.