# Grok 4.20 (Non-Reasoning) vs Kimi K2.6

> Grok 4.20 (Non-Reasoning) and Kimi K2.6 score almost the same on the Noometry Index (48.5 vs 47.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/grok-4-20-vs-kimi-k2-6
- Last updated: 2026-10-10
- Shared benchmarks: 36

## Summary

- They share 36 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 4 categories and Kimi K2.6 in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 39.6.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 44.9% for Grok 4.20 (Non-Reasoning) and 57.2% for Kimi K2.6.
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $0.95 / $4 for Kimi K2.6.
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 262K.
- Kimi K2.6 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 48.5 | 47.5 |
| Rank | 48 | 52 |
| Context | 1M | 262K |
| Input $/M | $1.25 | $0.95 |
| Output $/M | $2.50 | $4 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.20 (Non-Reasoning): 41.8 (#104)
- Kimi K2.6: 50.5 (#41)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| LMArena WebDev | 1374 | 1509 |
| WeirdML | 52.3% | 55.9% |
| LMArena Coding | 1458 | 1488 |
| ALE-Bench | 1,150 | 1,093 |
| SWE-bench Verified | — | 76.7% |
| SciCode | — | 53.5% |

## Agentic & Tool Use

- Grok 4.20 (Non-Reasoning): 34.3 (#43)
- Kimi K2.6: 21.8 (#128)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| Vending-Bench 2 | 4,663 | 6,205 |
| Terminal-Bench | 57.3% | — |
| OSWorld 2.0 | — | 4.6% |
| τ²-bench Banking | 18% | — |
| ExploitBench | — | 18.4% |
| GBAEval | — | 0.9% |
| GDP.pdf | — | 12% |
| LMArena Search | 1189 | — |

## Reasoning

- Grok 4.20 (Non-Reasoning): 52.2 (#30)
- Kimi K2.6: 39.6 (#51)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| NYT Connections (extended) | 85.4% | 87.2% |
| Chess Puzzles | 24% | 26% |
| LMArena Hard Prompts | 1451 | 1470 |
| DTBench | 90.1% | 90.9% |
| LMCA | 38.7% | 37.3% |
| Epoch Capabilities Index | 152.01 | 151.03 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 89.5% | — |
| CritPt | — | 8% |
| Thematic Generalization | 63.8% | — |
| EBR-Bench | — | 2.4% |
| Mystery Game Puzzles | — | 18% |
| ForecastBench | 61.4 | — |

## Math

- Grok 4.20 (Non-Reasoning): 48.0 (#54)
- Kimi K2.6: 56.8 (#34)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 57.2% |
| FrontierMath Tier 4 | 17.1% | 25.6% |
| OTIS Mock AIME 2024-2025 | 92.2% | 96.1% |
| ProofBench | 14% | 16% |
| LMArena Math | 1455 | 1475 |
| MathArena Final-Answer Competitions | — | 72.9% |
| FrontierMath (Feb 2025 set) | — | 39% |
| FrontierMath Tier 4 (v1) | — | 14.6% |

## Knowledge

- Grok 4.20 (Non-Reasoning): 52.8 (#54)
- Kimi K2.6: 53.9 (#48)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| GPQA Diamond | 89.3% | 90.8% |
| SimpleQA Verified | 30.2% | 34.9% |
| LMArena Expert | 1440 | 1491 |
| Vectara Hallucination Rate | — | 10.8% |

## Multimodal

- Grok 4.20 (Non-Reasoning): 33.2 (#88)
- Kimi K2.6: 31.8 (#95)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| LMArena Vision | 1263 | 1282 |
| Blueprint-Bench 2 | 0% | 3.9% |
| LMArena Document | 1416 | 1451 |
| Furniture Assembly | — | 21.7% |

## Multilingual

- Grok 4.20 (Non-Reasoning): 54.7 (#38)
- Kimi K2.6: 55.1 (#35)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| LMArena Non-English | 1440 | 1446 |
| LMArena Chinese | 1481 | 1521 |
| LMArena French | 1477 | 1471 |
| LMArena German | 1463 | 1449 |
| LMArena Japanese | 1450 | 1442 |
| LMArena Korean | 1417 | 1428 |
| LMArena Russian | 1457 | 1446 |
| LMArena Spanish | 1442 | 1463 |

## Instruction Following

- Grok 4.20 (Non-Reasoning): 75.0 (#79)
- Kimi K2.6: 76.5 (#40)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1451 |

## Long Context

- Grok 4.20 (Non-Reasoning): 45.4 (#33)
- Kimi K2.6: 44.9 (#50)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| LMArena Longer Query | 1436 | 1468 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |

## Writing & Preference

- Grok 4.20 (Non-Reasoning): 65.9 (#42)
- Kimi K2.6: 68.7 (#25)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2.6 |
|---|---|---|
| LMArena Text | 1451 | 1455 |
| LMArena Creative Writing | 1439 | 1434 |
| EQ-Bench Creative Writing | 1574 | 1725 |
| LMArena Multi-Turn | 1456 | 1453 |
| EQ-Bench 4 | — | 1202 |

## FAQ

### Is Grok 4.20 (Non-Reasoning) better than Kimi K2.6?

Grok 4.20 (Non-Reasoning) and Kimi K2.6 score almost the same on the Noometry Index (48.5 vs 47.5), so choose on price, context window or the category you care about most.

### Which is cheaper, Grok 4.20 (Non-Reasoning) or Kimi K2.6?

Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Kimi K2.6 lists at $0.95 and $4.

### Is Grok 4.20 (Non-Reasoning) or Kimi K2.6 better for coding?

Kimi K2.6 scores higher on coding benchmarks: 50.5 versus 41.8 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.20 (Non-Reasoning) does, with 1M tokens against 262K.

### How many benchmarks do Grok 4.20 (Non-Reasoning) and Kimi K2.6 share?

36 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Kimi K2.6 has 51.