# Kimi K3 vs Ministral 3B

> Kimi K3 is the stronger model overall, scoring 59.5 to 25.6 on the Noometry Index. Ministral 3B costs 150× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/kimi-k3-vs-ministral-3b
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Kimi K3 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 K3 leads 63.2 to 10.4.
- The biggest single-benchmark swing is GPQA Diamond: 93.1% for Kimi K3 and 25.3% for Ministral 3B.
- Ministral 3B is cheaper at $0.04 / $0.04 per million input/output tokens, against $3 / $15 for Kimi K3.
- Kimi K3 accepts more context: 1.05M tokens versus 128K.

## Snapshot

| | Kimi K3 | Ministral 3B |
|---|---|---|
| Provider | Moonshot AI | Mistral AI |
| Noometry Index | 59.5 | 25.6 |
| Rank | 12 | 336 |
| Context | 1.05M | 128K |
| Input $/M | $3 | $0.04 |
| Output $/M | $15 | $0.04 |
| Weights | Open | Open |

## Coding

- Kimi K3: 60.6 (#8)
- Ministral 3B: —

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1659 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| LMArena Coding | 1509 | — |
| ALE-Bench | 1,524 | — |

## Agentic & Tool Use

- Kimi K3: 41.8 (#19)
- Ministral 3B: —

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |

## Reasoning

- Kimi K3: 63.0 (#15)
- Ministral 3B: 17.7 (#278)

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| DTBench | 91.2% | 51.7% |
| LMCA | 52.7% | 5.5% |
| Epoch Capabilities Index | 157.68 | 118.08 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| LMArena Hard Prompts | 1495 | — |
| Mystery Game Puzzles | 26% | — |
| Surface Evolver Bench | 95% | — |
| ForecastBench | 61.1 | — |

## Math

- Kimi K3: 74.0 (#13)
- Ministral 3B: 24.5 (#257)

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |
| LMArena Math | 1493 | — |
| MATH Level 5 | — | 14.4% |

## Knowledge

- Kimi K3: 63.2 (#19)
- Ministral 3B: 10.4 (#297)

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| GPQA Diamond | 93.1% | 25.3% |
| SimpleQA Verified | 50.6% | — |
| Vectara Hallucination Rate | — | 7.3% |
| LMArena Expert | 1520 | — |

## Multimodal

- Kimi K3: 38.4 (#58)
- Ministral 3B: —

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |

## Multilingual

- Kimi K3: 56.5 (#20)
- Ministral 3B: —

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| LMArena Non-English | 1466 | — |
| LMArena Chinese | 1528 | — |
| LMArena French | 1488 | — |
| LMArena German | 1474 | — |
| LMArena Japanese | 1492 | — |
| LMArena Korean | 1465 | — |
| LMArena Russian | 1481 | — |
| LMArena Spanish | 1478 | — |

## Instruction Following

- Kimi K3: 77.8 (#13)
- Ministral 3B: —

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| LMArena Instruction Following | 1481 | — |

## Long Context

- Kimi K3: 45.8 (#27)
- Ministral 3B: —

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| LMArena Longer Query | 1494 | — |

## Writing & Preference

- Kimi K3: 76.7 (#4)
- Ministral 3B: —

| Benchmark | Kimi K3 | Ministral 3B |
|---|---|---|
| LMArena Text | 1476 | — |
| LMArena Creative Writing | 1452 | — |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
| LMArena Multi-Turn | 1488 | — |

## FAQ

### Is Kimi K3 better than Ministral 3B?

Kimi K3 is the stronger model overall, scoring 59.5 to 25.6 on the Noometry Index. Ministral 3B costs 150× less per token, which makes it the better buy when Kimi K3's lead doesn't matter for your workload.

### Which is cheaper, Kimi K3 or Ministral 3B?

Ministral 3B is cheaper. It lists at $0.04 per million input tokens and $0.04 per million output tokens; Kimi K3 lists at $3 and $15.

### Which has the bigger context window?

Kimi K3 does, with 1.05M tokens against 128K.

### How many benchmarks do Kimi K3 and Ministral 3B share?

4 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Ministral 3B has 6.