# Grok 4.7 vs Kimi K2.5

> Kimi K2.5 is the stronger model overall, scoring 47.8 to 46.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-4-7-vs-kimi-k2-5
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Grok 4.7 scores higher in 3 categories and Kimi K2.5 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2.5 leads 53.6 to 38.7.
- The biggest single-benchmark swing is CritPt: 17.7% for Grok 4.7 and 3.1% for Kimi K2.5.
- Kimi K2.5 is cheaper at $0.45 / $2.25 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.7 accepts more context: 500K tokens versus 262K.
- Kimi K2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 46.6 | 47.8 |
| Rank | 56 | 50 |
| Context | 500K | 262K |
| Input $/M | $2 | $0.45 |
| Output $/M | $6 | $2.25 |
| Weights | Proprietary | Open |

## Coding

- Grok 4.7: 55.0 (#23)
- Kimi K2.5: 48.7 (#48)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| LMArena WebDev | 1636 | 1436 |
| SciCode | 57.4% | 49% |
| LMArena Coding | 1423 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| CursorBench | 46.3% | — |
| SWE-bench Multilingual | — | 67.3% |
| FrontierSWE | 29.5% | — |
| WeirdML | — | 45.6% |
| ALE-Bench | — | 821.65 |

## Agentic & Tool Use

- Grok 4.7: —
- Kimi K2.5: 34.0 (#44)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |

## Reasoning

- Grok 4.7: 40.1 (#49)
- Kimi K2.5: 31.2 (#74)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| NYT Connections (extended) | 76.8% | 69.9% |
| CritPt | 17.7% | 3.1% |
| LMArena Hard Prompts | 1409 | 1454 |
| ARC-AGI-2 | — | 11.8% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 78.5% |
| ARC-AGI-1 | — | 65.3% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| Epoch Capabilities Index | — | 148.05 |

## Math

- Grok 4.7: 41.1 (#73)
- Kimi K2.5: 50.3 (#46)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Math | 1393 | 1470 |
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| ProofBench | 34% | — |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Grok 4.7: 38.7 (#130)
- Kimi K2.5: 53.6 (#52)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Expert | 1413 | 1466 |
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| Vectara Hallucination Rate | — | 14.2% |

## Multimodal

- Grok 4.7: 28.8 (#107)
- Kimi K2.5: 40.4 (#37)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| Furniture Assembly | 20.8% | — |
| LMArena Document | — | 1430 |

## Multilingual

- Grok 4.7: 51.2 (#108)
- Kimi K2.5: 54.1 (#50)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1392 | 1433 |
| LMArena Chinese | 1476 | 1495 |
| LMArena Russian | 1396 | 1436 |
| LMArena French | — | 1454 |
| LMArena German | — | 1441 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1412 |
| LMArena Spanish | — | 1450 |

## Instruction Following

- Grok 4.7: 74.3 (#98)
- Kimi K2.5: 75.5 (#60)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1406 | 1431 |

## Long Context

- Grok 4.7: 43.2 (#97)
- Kimi K2.5: 52.1 (#7)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Longer Query | 1416 | 1445 |
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |

## Writing & Preference

- Grok 4.7: 70.1 (#23)
- Kimi K2.5: 65.3 (#51)

| Benchmark | Grok 4.7 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1397 | 1445 |
| LMArena Creative Writing | 1391 | 1423 |
| EQ-Bench Creative Writing | 2007 | 1579 |
| LMArena Multi-Turn | 1389 | 1444 |

## FAQ

### Is Grok 4.7 better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 46.6 on the Noometry Index.

### Which is cheaper, Grok 4.7 or Kimi K2.5?

Kimi K2.5 is cheaper. It lists at $0.45 per million input tokens and $2.25 per million output tokens; Grok 4.7 lists at $2 and $6.

### Is Grok 4.7 or Kimi K2.5 better for coding?

Grok 4.7 scores higher on coding benchmarks: 55.0 versus 48.7 in the Noometry coding category.

### Which has the bigger context window?

Grok 4.7 does, with 500K tokens against 262K.

### How many benchmarks do Grok 4.7 and Kimi K2.5 share?

17 benchmarks have published results for both models. Grok 4.7 has 21 scored results on Noometry and Kimi K2.5 has 51.