# Kimi K2 (Jul 2025) vs Ministral 3B

> Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 25.6 on the Noometry Index. Ministral 3B costs 25× 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-ministral-3b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 3 categories and Ministral 3B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 (Jul 2025) leads 36.9 to 10.4.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 17.9% for Kimi K2 (Jul 2025) and 7.3% for Ministral 3B.
- Ministral 3B is cheaper at $0.04 / $0.04 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 128K.

## Snapshot

| | Kimi K2 (Jul 2025) | Ministral 3B |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 40.9 | 25.6 |
| Rank | 134 | 336 |
| Context | 262K | 128K |
| Input $/M | $0.57 | $0.04 |
| Output $/M | $2.30 | $0.04 |
| Weights | Open | Open |

## Coding

- Kimi K2 (Jul 2025): 43.1 (#83)
- Ministral 3B: —

| Benchmark | Kimi K2 (Jul 2025) | Ministral 3B |
|---|---|---|
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| LMArena Coding | 1399 | — |
| ALE-Bench | 597.5 | — |

## Agentic & Tool Use

- Kimi K2 (Jul 2025): 32.2 (#59)
- Ministral 3B: —

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

## Reasoning

- Kimi K2 (Jul 2025): 22.7 (#173)
- Ministral 3B: 17.7 (#278)

| Benchmark | Kimi K2 (Jul 2025) | Ministral 3B |
|---|---|---|
| Epoch Capabilities Index | 146.02 | 118.08 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| LMArena Hard Prompts | 1384 | — |
| DTBench | — | 51.7% |
| LMCA | — | 5.5% |
| ForecastBench | 60.2 | — |

## Math

- Kimi K2 (Jul 2025): 40.1 (#81)
- Ministral 3B: 24.5 (#257)

| Benchmark | Kimi K2 (Jul 2025) | Ministral 3B |
|---|---|---|
| Omni-MATH | 65.4% | — |
| LMArena Math | 1396 | — |
| MATH Level 5 | — | 14.4% |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Kimi K2 (Jul 2025): 36.9 (#153)
- Ministral 3B: 10.4 (#297)

| Benchmark | Kimi K2 (Jul 2025) | Ministral 3B |
|---|---|---|
| Vectara Hallucination Rate | 17.9% | 7.3% |
| GPQA Diamond | — | 25.3% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| GPQA (HELM) | 65.3% | — |
| LMArena Expert | 1363 | — |

## Multilingual

- Kimi K2 (Jul 2025): 49.8 (#125)
- Ministral 3B: —

| Benchmark | Kimi K2 (Jul 2025) | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1372 | — |
| LMArena Chinese | 1416 | — |
| LMArena French | 1379 | — |
| LMArena German | 1386 | — |
| LMArena Japanese | 1349 | — |
| LMArena Korean | 1324 | — |
| LMArena Russian | 1384 | — |
| LMArena Spanish | 1383 | — |

## Instruction Following

- Kimi K2 (Jul 2025): 71.3 (#151)
- Ministral 3B: —

| Benchmark | Kimi K2 (Jul 2025) | Ministral 3B |
|---|---|---|
| IFEval | 85% | — |
| LMArena Instruction Following | 1347 | — |

## Long Context

- Kimi K2 (Jul 2025): 41.2 (#140)
- Ministral 3B: —

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

## Writing & Preference

- Kimi K2 (Jul 2025): 62.5 (#76)
- Ministral 3B: —

| Benchmark | Kimi K2 (Jul 2025) | Ministral 3B |
|---|---|---|
| LMArena Text | 1380 | — |
| LMArena Creative Writing | 1349 | — |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
| LMArena Multi-Turn | 1371 | — |

## FAQ

### Is Kimi K2 (Jul 2025) better than Ministral 3B?

Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 25.6 on the Noometry Index. Ministral 3B costs 25× 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 Ministral 3B?

Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.

### Which has the bigger context window?

Kimi K2 (Jul 2025) does, with 262K tokens against 128K.

### How many benchmarks do Kimi K2 (Jul 2025) and Ministral 3B share?

2 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Ministral 3B has 6.