# Grok 3 vs Kimi K3

> Kimi K3 is the stronger model overall, scoring 59.5 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-3-vs-kimi-k3
- Last updated: 2026-10-10
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. Grok 3 scores higher in 0 categories and Kimi K3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 13.7.
- The biggest single-benchmark swing is ARC-AGI-1: 5.5% for Grok 3 and 94.5% for Kimi K3.
- Kimi K3 has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 3 | Kimi K3 |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 39.9 | 59.5 |
| Rank | 157 | 15 |
| Context | — | 1.05M |
| Input $/M | — | $3 |
| Output $/M | — | $15 |
| Weights | Proprietary | Open |

## Coding

- Grok 3: 41.9 (#115)
- Kimi K3: 61.0 (#10)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| WeirdML | 37.2% | 82.6% |
| LMArena Coding | 1432 | 1508 |
| DeepSWE | — | 68.5% |
| FrontierCode | — | 44.2% |
| Aider Polyglot | 53.3% | — |
| LMArena WebDev | — | 1654 |
| FrontierSWE | — | 25.9% |
| SciCode | — | 59.5% |
| ALE-Bench | — | 1,524 |

## Agentic & Tool Use

- Grok 3: 30.5 (#76)
- Kimi K3: 41.8 (#20)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| APEX-Agents | — | 50.6% |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 32% |
| BALROG | 29.5% | — |
| GBAEval | — | 48.3% |
| GDP.pdf | — | 19% |
| Vending-Bench 2 | — | 5,165 |

## Reasoning

- Grok 3: 13.7 (#333)
- Kimi K3: 63.0 (#17)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| ARC-AGI-2 | 0% | 60.4% |
| SimpleBench | 36.1% | 60.7% |
| ARC-AGI-1 | 5.5% | 94.5% |
| LMArena Hard Prompts | 1434 | 1496 |
| Epoch Capabilities Index | 138.33 | 157.45 |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 93.6% |
| CritPt | — | 23.4% |
| Chess Puzzles | — | 39% |
| Mystery Game Puzzles | — | 26% |
| DTBench | — | 91.2% |
| LMCA | — | 52.7% |
| Surface Evolver Bench | — | 95% |
| ForecastBench | — | 61.1 |

## Math

- Grok 3: 38.0 (#145)
- Kimi K3: 74.2 (#16)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 97.2% |
| LMArena Math | 1391 | 1491 |
| FrontierMath (Tiers 1-3) | — | 72.2% |
| FrontierMath Tier 4 | — | 39% |
| MathArena Final-Answer Competitions | — | 87.8% |
| ProofBench | — | 87% |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Grok 3: 46.2 (#82)
- Kimi K3: 63.2 (#21)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| GPQA Diamond | 75.8% | 93.1% |
| LMArena Expert | 1421 | 1521 |
| SimpleQA Verified | — | 50.6% |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |

## Multimodal

- Grok 3: —
- Kimi K3: 37.8 (#70)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| Blueprint-Bench 2 | — | 29.5% |
| Furniture Assembly | — | 34.2% |

## Multilingual

- Grok 3: 52.3 (#87)
- Kimi K3: 56.3 (#21)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| LMArena Non-English | 1410 | 1466 |
| LMArena Chinese | 1448 | 1529 |
| LMArena French | 1460 | 1491 |
| LMArena German | 1431 | 1488 |
| LMArena Japanese | 1387 | 1487 |
| LMArena Korean | 1373 | 1458 |
| LMArena Russian | 1416 | 1482 |
| LMArena Spanish | 1417 | 1472 |

## Instruction Following

- Grok 3: 75.0 (#73)
- Kimi K3: 77.7 (#14)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| LMArena Instruction Following | 1409 | 1483 |
| IFEval | 88.4% | — |

## Long Context

- Grok 3: 38.7 (#192)
- Kimi K3: 45.8 (#29)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| LMArena Longer Query | 1439 | 1494 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- Grok 3: 55.8 (#141)
- Kimi K3: 76.6 (#4)

| Benchmark | Grok 3 | Kimi K3 |
|---|---|---|
| LMArena Text | 1426 | 1476 |
| LMArena Creative Writing | 1414 | 1454 |
| EQ-Bench Creative Writing | 1186 | 2082 |
| LMArena Multi-Turn | 1425 | 1488 |
| Short-Story Creative Writing | 76.4% | — |
| WildBench | 84.9% | — |
| EQ-Bench 4 | — | 1339 |

## FAQ

### Is Grok 3 better than Kimi K3?

Kimi K3 is the stronger model overall, scoring 59.5 to 39.9 on the Noometry Index.

### Is Grok 3 or Kimi K3 better for coding?

Kimi K3 scores higher on coding benchmarks: 61.0 versus 41.9 in the Noometry coding category.

### How many benchmarks do Grok 3 and Kimi K3 share?

25 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Kimi K3 has 53.