# Kimi K2 Thinking Turbo vs Mistral Small 3

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 30.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-thinking-turbo-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 45.5 to 15.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.1% for Kimi K2 Thinking Turbo and 6.7% for Mistral Small 3.

## Snapshot

| | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 45.4 | 30.9 |
| Rank | 63 | 268 |
| Context | — | 33K |
| Input $/M | — | $0.05 |
| Output $/M | — | $0.08 |
| Weights | Open | Open |

## Coding

- Kimi K2 Thinking Turbo: 38.1 (#166)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1454 | 1246 |
| LMArena WebDev | 1322 | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |

## Reasoning

- Kimi K2 Thinking Turbo: 31.4 (#72)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| Chess Puzzles | 20% | 0% |
| LMArena Hard Prompts | 1428 | 1233 |
| Epoch Capabilities Index | — | 127.06 |

## Math

- Kimi K2 Thinking Turbo: 45.5 (#62)
- Mistral Small 3: 15.3 (#290)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | 6.7% |
| LMArena Math | 1429 | 1240 |

## Knowledge

- Kimi K2 Thinking Turbo: 50.9 (#64)
- Mistral Small 3: 25.0 (#258)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| GPQA Diamond | 84.2% | 47.3% |
| LMArena Expert | 1439 | 1202 |
| Confabulations | — | 25.2% |

## Multilingual

- Kimi K2 Thinking Turbo: 51.6 (#104)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1398 | 1198 |
| LMArena Chinese | 1457 | 1204 |
| LMArena French | 1425 | 1202 |
| LMArena German | 1390 | 1211 |
| LMArena Japanese | 1356 | 1111 |
| LMArena Korean | 1329 | 1188 |
| LMArena Russian | 1390 | 1216 |
| LMArena Spanish | 1407 | — |

## Instruction Following

- Kimi K2 Thinking Turbo: 74.2 (#103)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1214 |

## Long Context

- Kimi K2 Thinking Turbo: 43.2 (#99)
- Mistral Small 3: 37.8 (#206)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1415 | 1246 |

## Writing & Preference

- Kimi K2 Thinking Turbo: 60.2 (#99)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1415 | 1234 |
| LMArena Creative Writing | 1373 | 1195 |
| LMArena Multi-Turn | 1414 | 1217 |
| EQ-Bench Creative Writing | — | 707 |

## FAQ

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

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 30.9 on the Noometry Index.

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

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 36.0 in the Noometry coding category.

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

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