# Kimi K2.6 vs Step 5 Preview

> Kimi K2.6 and Step 5 Preview score almost the same on the Noometry Index (47.7 vs 47.9), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/kimi-k2-6-vs-step-5-preview
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Kimi K2.6 scores higher in 7 categories and Step 5 Preview in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.6 leads 54.0 to 41.2.
- The biggest single-benchmark swing is ProofBench: 16% for Kimi K2.6 and 42% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Step 5 Preview accepts more context: 1.02M tokens versus 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| Provider | Moonshot AI | StepFun |
| Noometry Index | 47.7 | 47.9 |
| Rank | 60 | 58 |
| Context | 262K | 1.02M |
| Input $/M | $0.95 | $1 |
| Output $/M | $4 | $2.70 |
| Weights | Open | Proprietary |

## Coding

- Kimi K2.6: 50.7 (#43)
- Step 5 Preview: 51.8 (#36)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1509 | 1564 |
| SciCode | 53.5% | 58.9% |
| LMArena Coding | 1488 | 1480 |
| SWE-bench Verified | 76.7% | — |
| WeirdML | 55.9% | — |
| ALE-Bench | 1,093 | — |

## Agentic & Tool Use

- Kimi K2.6: 21.9 (#137)
- Step 5 Preview: —

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

## Reasoning

- Kimi K2.6: 40.5 (#55)
- Step 5 Preview: 40.0 (#57)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| CritPt | 8% | 20.9% |
| LMArena Hard Prompts | 1470 | 1465 |
| NYT Connections (extended) | 87.2% | — |
| Chess Puzzles | 26% | — |
| EBR-Bench | 2.4% | — |
| Mystery Game Puzzles | 18% | — |
| DTBench | 90.9% | — |
| LMCA | 37.3% | — |
| Epoch Capabilities Index | 151.05 | — |

## Math

- Kimi K2.6: 57.0 (#41)
- Step 5 Preview: 46.1 (#72)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| ProofBench | 16% | 42% |
| LMArena Math | 1475 | 1470 |
| 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: 54.0 (#54)
- Step 5 Preview: 41.2 (#112)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1491 | 1470 |
| GPQA Diamond | 90.8% | — |
| SimpleQA Verified | 34.9% | — |
| Vectara Hallucination Rate | 10.8% | — |

## Multimodal

- Kimi K2.6: 31.6 (#103)
- Step 5 Preview: 41.0 (#41)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1283 | 1267 |
| Blueprint-Bench 2 | 3.9% | — |
| Furniture Assembly | 21.7% | — |
| LMArena Document | 1451 | — |

## Multilingual

- Kimi K2.6: 54.9 (#37)
- Step 5 Preview: 53.8 (#54)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1446 | 1432 |
| LMArena Chinese | 1521 | 1519 |
| LMArena Russian | 1446 | 1436 |
| LMArena Spanish | 1464 | 1439 |
| LMArena French | 1471 | — |
| LMArena German | 1450 | — |
| LMArena Japanese | 1443 | — |
| LMArena Korean | 1427 | — |

## Instruction Following

- Kimi K2.6: 76.3 (#43)
- Step 5 Preview: 76.0 (#50)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1451 | 1444 |

## Long Context

- Kimi K2.6: 44.9 (#52)
- Step 5 Preview: 44.5 (#64)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1468 | 1455 |

## Writing & Preference

- Kimi K2.6: 68.5 (#26)
- Step 5 Preview: 62.8 (#71)

| Benchmark | Kimi K2.6 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1455 | 1442 |
| LMArena Creative Writing | 1434 | 1410 |
| LMArena Multi-Turn | 1453 | 1447 |
| EQ-Bench Creative Writing | 1725 | — |
| EQ-Bench 4 | 1202 | — |

## FAQ

### Is Kimi K2.6 better than Step 5 Preview?

Kimi K2.6 and Step 5 Preview score almost the same on the Noometry Index (47.7 vs 47.9), so choose on price, context window or the category you care about most.

### Which is cheaper, Kimi K2.6 or Step 5 Preview?

Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Kimi K2.6 lists at $0.95 and $4.

### Is Kimi K2.6 or Step 5 Preview better for coding?

Step 5 Preview scores higher on coding benchmarks: 51.8 versus 50.7 in the Noometry coding category.

### Which has the bigger context window?

Step 5 Preview does, with 1.02M tokens against 262K.

### How many benchmarks do Kimi K2.6 and Step 5 Preview share?

18 benchmarks have published results for both models. Kimi K2.6 has 51 scored results on Noometry and Step 5 Preview has 18.