# Grok 4.20 (Non-Reasoning) vs Kimi K2 (Jul 2025)

> Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 1.6× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/grok-4-20-vs-kimi-k2
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Kimi K2 (Jul 2025) in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 23.3.
- The biggest single-benchmark swing is Terminal-Bench: 57.3% for Grok 4.20 (Non-Reasoning) and 35.7% for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 262K.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 48.6 | 41.2 |
| Rank | 54 | 140 |
| Context | 1M | 262K |
| Input $/M | $1.25 | $0.57 |
| Output $/M | $2.50 | $2.30 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.20 (Non-Reasoning): 42.1 (#112)
- Kimi K2 (Jul 2025): 42.4 (#102)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| WeirdML | 52.3% | 42.8% |
| LMArena Coding | 1459 | 1399 |
| ALE-Bench | 1,150 | 597.5 |
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1375 | — |
| GSO | — | 4.9% |

## Agentic & Tool Use

- Grok 4.20 (Non-Reasoning): 34.4 (#46)
- Kimi K2 (Jul 2025): 32.4 (#64)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | 57.3% | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| METR Time Horizons | — | 59.2% |
| Vending-Bench 2 | 4,663 | — |

## Reasoning

- Grok 4.20 (Non-Reasoning): 52.3 (#32)
- Kimi K2 (Jul 2025): 23.3 (#179)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| Kagi LLM Benchmark | 75% | 64.4% |
| LMArena Hard Prompts | 1451 | 1384 |
| Epoch Capabilities Index | 151.98 | 146.01 |
| ForecastBench | 61.4 | 60.2 |
| ARC-AGI-2 | 65.1% | — |
| SimpleBench | — | 26.3% |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| DTBench | 90.1% | — |
| LMCA | 38.7% | — |

## Math

- Grok 4.20 (Non-Reasoning): 48.2 (#65)
- Kimi K2 (Jul 2025): 42.7 (#83)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Math | 1455 | 1397 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
| Omni-MATH | — | 65.4% |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Grok 4.20 (Non-Reasoning): 52.8 (#60)
- Kimi K2 (Jul 2025): 37.3 (#157)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Expert | 1439 | 1365 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |

## Multimodal

- Grok 4.20 (Non-Reasoning): 33.3 (#98)
- Kimi K2 (Jul 2025): —

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |

## Multilingual

- Grok 4.20 (Non-Reasoning): 54.5 (#40)
- Kimi K2 (Jul 2025): 49.6 (#130)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 1441 | 1372 |
| LMArena Chinese | 1481 | 1415 |
| LMArena French | 1476 | 1379 |
| LMArena German | 1465 | 1387 |
| LMArena Japanese | 1449 | 1349 |
| LMArena Korean | 1417 | 1325 |
| LMArena Russian | 1458 | 1385 |
| LMArena Spanish | 1443 | 1386 |

## Instruction Following

- Grok 4.20 (Non-Reasoning): 74.8 (#83)
- Kimi K2 (Jul 2025): 71.1 (#156)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1420 | 1348 |
| IFEval | — | 85% |

## Long Context

- Grok 4.20 (Non-Reasoning): 45.5 (#34)
- Kimi K2 (Jul 2025): 41.2 (#145)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| CL-bench | 22.2% | 17.6% |
| LMArena Longer Query | 1437 | 1353 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench Life | 11.9% | — |

## Writing & Preference

- Grok 4.20 (Non-Reasoning): 65.7 (#44)
- Kimi K2 (Jul 2025): 62.3 (#78)

| Benchmark | Grok 4.20 (Non-Reasoning) | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1451 | 1380 |
| LMArena Creative Writing | 1438 | 1350 |
| EQ-Bench Creative Writing | 1574 | 1666 |
| LMArena Multi-Turn | 1456 | 1371 |
| Short-Story Creative Writing | — | 85.6% |
| WildBench | — | 86.2% |

## FAQ

### Is Grok 4.20 (Non-Reasoning) better than Kimi K2 (Jul 2025)?

Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 41.2 on the Noometry Index. Kimi K2 (Jul 2025) costs 1.6× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.

### Which is cheaper, Grok 4.20 (Non-Reasoning) or Kimi K2 (Jul 2025)?

Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.

### Is Grok 4.20 (Non-Reasoning) or Kimi K2 (Jul 2025) better for coding?

They score almost the same on coding (42.1 vs 42.4); test both on your own repository before choosing.

### 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 (Jul 2025) share?

25 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Kimi K2 (Jul 2025) has 42.