# Grok 3 vs Kimi K2.5

> Kimi K2.5 is the stronger model overall, scoring 48.1 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-vs-kimi-k2-5
- Last updated: 2026-10-10
- Shared benchmarks: 30

## Summary

- They share 30 benchmarks with published results for both. Grok 3 scores higher in 0 categories and Kimi K2.5 in 9 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2.5 leads 31.2 to 13.7.
- The biggest single-benchmark swing is ARC-AGI-1: 5.5% for Grok 3 and 65.3% for Kimi K2.5.
- Kimi K2.5 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 3 | Kimi K2.5 |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 39.9 | 48.1 |
| Rank | 157 | 57 |
| Context | — | 262K |
| Input $/M | — | $0.45 |
| Output $/M | — | $2.25 |
| Weights | Proprietary | Open |

## Coding

- Grok 3: 41.9 (#115)
- Kimi K2.5: 48.8 (#53)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| WeirdML | 37.2% | 45.6% |
| LMArena Coding | 1432 | 1474 |
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1437 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| ALE-Bench | — | 821.65 |

## Agentic & Tool Use

- Grok 3: 30.5 (#76)
- Kimi K2.5: 34.2 (#48)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| BALROG | 29.5% | — |
| Vending-Bench 2 | — | 1,198 |

## Reasoning

- Grok 3: 13.7 (#333)
- Kimi K2.5: 31.2 (#80)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| ARC-AGI-2 | 0% | 11.8% |
| SimpleBench | 36.1% | 46.8% |
| Kagi LLM Benchmark | 61.3% | 78.5% |
| ARC-AGI-1 | 5.5% | 65.3% |
| LMArena Hard Prompts | 1434 | 1453 |
| Epoch Capabilities Index | 138.33 | 148.03 |
| NYT Connections (extended) | — | 69.9% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |

## Math

- Grok 3: 38.0 (#145)
- Kimi K2.5: 51.8 (#53)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 92.2% |
| LMArena Math | 1391 | 1470 |
| FrontierMath (Feb 2025 set) | 3.8% | 27.9% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| MathArena Final-Answer Competitions | — | 62.3% |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |

## Knowledge

- Grok 3: 46.2 (#82)
- Kimi K2.5: 53.6 (#56)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | 75.8% | 87.6% |
| Vectara Hallucination Rate | 5.8% | 14.2% |
| LMArena Expert | 1421 | 1466 |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| GPQA (HELM) | 65% | — |

## Multimodal

- Grok 3: —
- Kimi K2.5: 41.1 (#39)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |

## Multilingual

- Grok 3: 52.3 (#87)
- Kimi K2.5: 53.9 (#53)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 1410 | 1433 |
| LMArena Chinese | 1448 | 1495 |
| LMArena French | 1460 | 1454 |
| LMArena German | 1431 | 1441 |
| LMArena Japanese | 1387 | 1421 |
| LMArena Korean | 1373 | 1410 |
| LMArena Russian | 1416 | 1435 |
| LMArena Spanish | 1417 | 1450 |

## Instruction Following

- Grok 3: 75.0 (#73)
- Kimi K2.5: 75.3 (#64)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1431 |
| IFEval | 88.4% | — |

## Long Context

- Grok 3: 38.7 (#192)
- Kimi K2.5: 52.1 (#7)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| Fiction.LiveBench | 58.3% | 86.1% |
| LMArena Longer Query | 1439 | 1445 |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |

## Writing & Preference

- Grok 3: 55.8 (#141)
- Kimi K2.5: 65.1 (#53)

| Benchmark | Grok 3 | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1426 | 1445 |
| LMArena Creative Writing | 1414 | 1423 |
| EQ-Bench Creative Writing | 1186 | 1579 |
| LMArena Multi-Turn | 1425 | 1444 |
| Short-Story Creative Writing | 76.4% | — |
| WildBench | 84.9% | — |

## FAQ

### Is Grok 3 better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 48.1 to 39.9 on the Noometry Index.

### Is Grok 3 or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.8 versus 41.9 in the Noometry coding category.

### How many benchmarks do Grok 3 and Kimi K2.5 share?

30 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Kimi K2.5 has 51.