# Kimi K2.6 vs MiniMax-M2.7

> Kimi K2.6 is the stronger model overall, scoring 47.5 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 3.3× 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-minimax-m2-7
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. Kimi K2.6 scores higher in 8 categories and MiniMax-M2.7 in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.6 leads 56.8 to 24.9.
- The biggest single-benchmark swing is NYT Connections (extended): 87.2% for Kimi K2.6 and 24.7% for MiniMax-M2.7.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Kimi K2.6 accepts more context: 262K tokens versus 205K.

## Snapshot

| | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| Provider | Moonshot AI | MiniMax |
| Noometry Index | 47.5 | 37.4 |
| Rank | 52 | 188 |
| Context | 262K | 205K |
| Input $/M | $0.95 | $0.30 |
| Output $/M | $4 | $1.20 |
| Weights | Open | Open |

## Coding

- Kimi K2.6: 50.5 (#41)
- MiniMax-M2.7: 41.4 (#115)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena WebDev | 1509 | 1397 |
| SciCode | 53.5% | 47% |
| WeirdML | 55.9% | 37% |
| LMArena Coding | 1488 | 1454 |
| ALE-Bench | 1,093 | 599.25 |
| SWE-bench Verified | 76.7% | — |

## Agentic & Tool Use

- Kimi K2.6: 21.8 (#128)
- MiniMax-M2.7: 24.9 (#103)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| ExploitBench | 18.4% | 13.3% |
| GBAEval | 0.9% | 0% |
| Terminal-Bench | — | 45.1% |
| OSWorld 2.0 | 4.6% | — |
| GDP.pdf | 12% | — |
| Vending-Bench 2 | 6,205 | — |

## Reasoning

- Kimi K2.6: 39.6 (#51)
- MiniMax-M2.7: 19.0 (#248)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| NYT Connections (extended) | 87.2% | 24.7% |
| CritPt | 8% | 0.6% |
| LMArena Hard Prompts | 1470 | 1422 |
| Epoch Capabilities Index | 151.03 | 145.84 |
| Chess Puzzles | 26% | — |
| Thematic Generalization | — | 39.3% |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 18% | — |
| DTBench | 90.9% | — |
| LMCA | 37.3% | — |

## Math

- Kimi K2.6: 56.8 (#34)
- MiniMax-M2.7: 24.9 (#254)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| ProofBench | 16% | 3% |
| LMArena Math | 1475 | 1420 |
| 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)
- MiniMax-M2.7: 37.1 (#151)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | 10.8% | 12.9% |
| LMArena Expert | 1491 | 1443 |
| GPQA Diamond | 90.8% | — |
| SimpleQA Verified | 34.9% | — |

## Multimodal

- Kimi K2.6: 31.8 (#95)
- MiniMax-M2.7: —

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Vision | 1282 | — |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |

## Multilingual

- Kimi K2.6: 55.1 (#35)
- MiniMax-M2.7: 50.5 (#120)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1446 | 1382 |
| LMArena Chinese | 1521 | 1439 |
| LMArena French | 1471 | 1422 |
| LMArena German | 1449 | 1398 |
| LMArena Japanese | 1442 | 1261 |
| LMArena Korean | 1428 | 1313 |
| LMArena Russian | 1446 | 1383 |
| LMArena Spanish | 1463 | 1403 |

## Instruction Following

- Kimi K2.6: 76.5 (#40)
- MiniMax-M2.7: 74.2 (#101)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1404 |

## Long Context

- Kimi K2.6: 44.9 (#50)
- MiniMax-M2.7: 43.3 (#94)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1468 | 1419 |

## Writing & Preference

- Kimi K2.6: 68.7 (#25)
- MiniMax-M2.7: 59.1 (#107)

| Benchmark | Kimi K2.6 | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1455 | 1404 |
| LMArena Creative Writing | 1434 | 1354 |
| LMArena Multi-Turn | 1453 | 1413 |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |

## FAQ

### Is Kimi K2.6 better than MiniMax-M2.7?

Kimi K2.6 is the stronger model overall, scoring 47.5 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 3.3× 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 MiniMax-M2.7?

MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Kimi K2.6 lists at $0.95 and $4.

### Is Kimi K2.6 or MiniMax-M2.7 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 41.4 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2.6 does, with 262K tokens against 205K.

### How many benchmarks do Kimi K2.6 and MiniMax-M2.7 share?

28 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and MiniMax-M2.7 has 30.