# Kimi K2 (Jul 2025) vs Mistral Small 3

> Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 30.9 on the Noometry Index. Mistral Small 3 costs 17× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.

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

## Summary

- They share 19 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.5 to 32.4.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 33K.

## Snapshot

| | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 40.9 | 30.9 |
| Rank | 134 | 268 |
| Context | 262K | 33K |
| Input $/M | $0.57 | $0.05 |
| Output $/M | $2.30 | $0.08 |
| Weights | Open | Open |

## Coding

- Kimi K2 (Jul 2025): 43.1 (#83)
- Mistral Small 3: 36.0 (#203)

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1399 | 1246 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 597.5 | — |

## Agentic & Tool Use

- Kimi K2 (Jul 2025): 32.2 (#59)
- Mistral Small 3: —

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |

## Reasoning

- Kimi K2 (Jul 2025): 22.7 (#173)
- Mistral Small 3: 18.2 (#269)

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1233 |
| Epoch Capabilities Index | 146.02 | 127.06 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| Chess Puzzles | — | 0% |
| ForecastBench | 60.2 | — |

## Math

- Kimi K2 (Jul 2025): 40.1 (#81)
- Mistral Small 3: 15.3 (#290)

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1396 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Kimi K2 (Jul 2025): 36.9 (#153)
- Mistral Small 3: 25.0 (#258)

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| Confabulations | 20.4% | 25.2% |
| LMArena Expert | 1363 | 1202 |
| GPQA Diamond | — | 47.3% |
| MMLU-Pro | 81.9% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |

## Multilingual

- Kimi K2 (Jul 2025): 49.8 (#125)
- Mistral Small 3: 37.5 (#231)

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1372 | 1198 |
| LMArena Chinese | 1416 | 1204 |
| LMArena French | 1379 | 1202 |
| LMArena German | 1386 | 1211 |
| LMArena Japanese | 1349 | 1111 |
| LMArena Korean | 1324 | 1188 |
| LMArena Russian | 1384 | 1216 |
| LMArena Spanish | 1383 | — |

## Instruction Following

- Kimi K2 (Jul 2025): 71.3 (#151)
- Mistral Small 3: 63.9 (#224)

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1347 | 1214 |
| IFEval | 85% | — |

## Long Context

- Kimi K2 (Jul 2025): 41.2 (#140)
- Mistral Small 3: 37.8 (#206)

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1353 | 1246 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |

## Writing & Preference

- Kimi K2 (Jul 2025): 62.5 (#76)
- Mistral Small 3: 32.4 (#275)

| Benchmark | Kimi K2 (Jul 2025) | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1380 | 1234 |
| LMArena Creative Writing | 1349 | 1195 |
| EQ-Bench Creative Writing | 1666 | 707 |
| LMArena Multi-Turn | 1371 | 1217 |
| Short-Story Creative Writing | 85.6% | — |
| WildBench | 86.2% | — |

## FAQ

### Is Kimi K2 (Jul 2025) better than Mistral Small 3?

Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 30.9 on the Noometry Index. Mistral Small 3 costs 17× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.

### Which is cheaper, Kimi K2 (Jul 2025) or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.

### Is Kimi K2 (Jul 2025) or Mistral Small 3 better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 36.0 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2 (Jul 2025) does, with 262K tokens against 33K.

### How many benchmarks do Kimi K2 (Jul 2025) and Mistral Small 3 share?

19 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Mistral Small 3 has 24.