# Grok-2 (Dec 2024) vs Kimi K2 Thinking Turbo

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/grok-2-vs-kimi-k2-thinking-turbo
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Kimi K2 Thinking Turbo in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 45.5 to 19.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 11.5% for Grok-2 (Dec 2024) and 83.1% for Kimi K2 Thinking Turbo.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.

## Snapshot

| | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| Provider | xAI | Moonshot AI |
| Noometry Index | 33.4 | 45.4 |
| Rank | 233 | 63 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Grok-2 (Dec 2024): 32.9 (#254)
- Kimi K2 Thinking Turbo: 38.1 (#166)

| Benchmark | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Coding | 1288 | 1454 |
| LMArena WebDev | — | 1322 |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |

## Reasoning

- Grok-2 (Dec 2024): 16.4 (#294)
- Kimi K2 Thinking Turbo: 31.4 (#72)

| Benchmark | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1428 |
| SimpleBench | 22.7% | — |
| Chess Puzzles | — | 20% |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| Epoch Capabilities Index | 130.48 | — |
| LiveBench | 54.3% | — |

## Math

- Grok-2 (Dec 2024): 19.6 (#278)
- Kimi K2 Thinking Turbo: 45.5 (#62)

| Benchmark | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 11.5% | 83.1% |
| LMArena Math | 1283 | 1429 |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |

## Knowledge

- Grok-2 (Dec 2024): 29.8 (#225)
- Kimi K2 Thinking Turbo: 50.9 (#64)

| Benchmark | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| GPQA Diamond | 53.8% | 84.2% |
| LMArena Expert | 1254 | 1439 |
| Confabulations | 20.1% | — |

## Multilingual

- Grok-2 (Dec 2024): 43.3 (#183)
- Kimi K2 Thinking Turbo: 51.6 (#104)

| Benchmark | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Non-English | 1282 | 1398 |
| LMArena Chinese | 1289 | 1457 |
| LMArena French | 1317 | 1425 |
| LMArena German | 1287 | 1390 |
| LMArena Japanese | 1244 | 1356 |
| LMArena Korean | 1237 | 1329 |
| LMArena Russian | 1286 | 1390 |
| LMArena Spanish | 1281 | 1407 |

## Instruction Following

- Grok-2 (Dec 2024): 67.1 (#197)
- Kimi K2 Thinking Turbo: 74.2 (#103)

| Benchmark | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Instruction Following | 1270 | 1403 |
| LiveBench Instruction Following | 69.6% | — |

## Long Context

- Grok-2 (Dec 2024): 38.7 (#186)
- Kimi K2 Thinking Turbo: 43.2 (#99)

| Benchmark | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Longer Query | 1276 | 1415 |

## Writing & Preference

- Grok-2 (Dec 2024): 48.8 (#192)
- Kimi K2 Thinking Turbo: 60.2 (#99)

| Benchmark | Grok-2 (Dec 2024) | Kimi K2 Thinking Turbo |
|---|---|---|
| LMArena Text | 1305 | 1415 |
| LMArena Creative Writing | 1284 | 1373 |
| LMArena Multi-Turn | 1290 | 1414 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |

## FAQ

### Is Grok-2 (Dec 2024) better than Kimi K2 Thinking Turbo?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 33.4 on the Noometry Index.

### Is Grok-2 (Dec 2024) or Kimi K2 Thinking Turbo better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 32.9 in the Noometry coding category.

### How many benchmarks do Grok-2 (Dec 2024) and Kimi K2 Thinking Turbo share?

19 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Kimi K2 Thinking Turbo has 21.