# Kimi K2 Thinking Turbo vs Mistral Small

> Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 33.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-thinking-turbo-vs-mistral-small
- 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 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 15.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 83.1% for Kimi K2 Thinking Turbo and 5.8% for Mistral Small.

## Snapshot

| | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 45.4 | 33.1 |
| Rank | 63 | 238 |
| Context | — | 256K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Open | Open |

## Coding

- Kimi K2 Thinking Turbo: 38.1 (#166)
- Mistral Small: 33.5 (#242)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| LMArena Coding | 1454 | 1363 |
| LMArena WebDev | 1322 | — |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- Kimi K2 Thinking Turbo: —
- Mistral Small: 27.9 (#87)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- Kimi K2 Thinking Turbo: 31.4 (#72)
- Mistral Small: 19.3 (#238)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1336 |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| Chess Puzzles | 20% | — |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |

## Math

- Kimi K2 Thinking Turbo: 45.5 (#62)
- Mistral Small: 15.4 (#287)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.1% | 5.8% |
| LMArena Math | 1429 | 1341 |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Kimi K2 Thinking Turbo: 50.9 (#64)
- Mistral Small: 30.9 (#214)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| GPQA Diamond | 84.2% | 47.5% |
| LMArena Expert | 1439 | 1293 |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |

## Multimodal

- Kimi K2 Thinking Turbo: —
- Mistral Small: 32.9 (#91)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- Kimi K2 Thinking Turbo: 51.6 (#104)
- Mistral Small: 45.7 (#164)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| LMArena Non-English | 1398 | 1315 |
| LMArena Chinese | 1457 | 1342 |
| LMArena French | 1425 | 1337 |
| LMArena German | 1390 | 1341 |
| LMArena Japanese | 1356 | 1275 |
| LMArena Korean | 1329 | 1260 |
| LMArena Russian | 1390 | 1324 |
| LMArena Spanish | 1407 | 1346 |

## Instruction Following

- Kimi K2 Thinking Turbo: 74.2 (#103)
- Mistral Small: 66.6 (#204)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1403 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Kimi K2 Thinking Turbo: 43.2 (#99)
- Mistral Small: 40.4 (#151)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1415 | 1327 |

## Writing & Preference

- Kimi K2 Thinking Turbo: 60.2 (#99)
- Mistral Small: 52.6 (#165)

| Benchmark | Kimi K2 Thinking Turbo | Mistral Small |
|---|---|---|
| LMArena Text | 1415 | 1338 |
| LMArena Creative Writing | 1373 | 1304 |
| LMArena Multi-Turn | 1414 | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

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

Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.4 to 33.1 on the Noometry Index.

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

Kimi K2 Thinking Turbo scores higher on coding benchmarks: 38.1 versus 33.5 in the Noometry coding category.

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

19 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Mistral Small has 39.