# Kimi K2 Thinking Turbo vs Mistral Large 3

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 38.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-thinking-turbo-vs-mistral-large-3
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 7 categories and Mistral Large 3 in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K2 Thinking Turbo leads 31.4 to 14.6.

## Snapshot

| | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 45.4 | 38.6 |
| Rank | 63 | 172 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.75 |
| Weights | Open | Open |

## Coding

- Kimi K2 Thinking Turbo: 38.1 (#166)
- Mistral Large 3: 34.1 (#230)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1322 | 1230 |
| LMArena Coding | 1454 | 1447 |

## Reasoning

- Kimi K2 Thinking Turbo: 31.4 (#72)
- Mistral Large 3: 14.6 (#314)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Chess Puzzles | 20% | — |
| Thematic Generalization | — | 23% |

## Math

- Kimi K2 Thinking Turbo: 45.5 (#62)
- Mistral Large 3: 36.0 (#131)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1429 | 1415 |
| OTIS Mock AIME 2024-2025 | 83.1% | — |

## Knowledge

- Kimi K2 Thinking Turbo: 50.9 (#64)
- Mistral Large 3: 35.5 (#173)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1439 | 1421 |
| GPQA Diamond | 84.2% | — |
| Vectara Hallucination Rate | — | 14.5% |

## Multimodal

- Kimi K2 Thinking Turbo: —
- Mistral Large 3: 37.6 (#65)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- Kimi K2 Thinking Turbo: 51.6 (#104)
- Mistral Large 3: 52.6 (#79)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1398 | 1412 |
| LMArena Chinese | 1457 | 1448 |
| LMArena French | 1425 | 1456 |
| LMArena German | 1390 | 1438 |
| LMArena Japanese | 1356 | 1399 |
| LMArena Korean | 1329 | 1384 |
| LMArena Russian | 1390 | 1412 |
| LMArena Spanish | 1407 | 1437 |

## Instruction Following

- Kimi K2 Thinking Turbo: 74.2 (#103)
- Mistral Large 3: 74.1 (#104)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1402 |

## Long Context

- Kimi K2 Thinking Turbo: 43.2 (#99)
- Mistral Large 3: 43.1 (#102)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1415 | 1413 |

## Writing & Preference

- Kimi K2 Thinking Turbo: 60.2 (#99)
- Mistral Large 3: 60.2 (#100)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1415 | 1427 |
| LMArena Creative Writing | 1373 | 1385 |
| LMArena Multi-Turn | 1414 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |

## FAQ

### Is Kimi K2 Thinking Turbo better than Mistral Large 3?

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 38.6 on the Noometry Index.

### Is Kimi K2 Thinking Turbo or Mistral Large 3 better for coding?

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 34.1 in the Noometry coding category.

### How many benchmarks do Kimi K2 Thinking Turbo and Mistral Large 3 share?

18 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Mistral Large 3 has 24.