# Kimi K3 vs Phi 3 Mini 128k Instruct

> Kimi K3 is the stronger model overall, scoring 59.5 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k3-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Phi 3 Mini 128k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K3 leads 76.7 to 27.3.

## Snapshot

| | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | Moonshot AI | Microsoft |
| Noometry Index | 59.5 | 29.1 |
| Rank | 12 | 303 |
| Context | 1.05M | — |
| Input $/M | $3 | — |
| Output $/M | $15 | — |
| Weights | Open | Open |

## Coding

- Kimi K3: 60.6 (#8)
- Phi 3 Mini 128k Instruct: 28.3 (#307)

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1509 | 1040 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1659 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 1,524 | — |

## Agentic & Tool Use

- Kimi K3: 41.8 (#19)
- Phi 3 Mini 128k Instruct: —

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| 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)
- Phi 3 Mini 128k Instruct: 18.7 (#254)

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1495 | 1028 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| Epoch Capabilities Index | 157.68 | — |
| ForecastBench | 61.1 | — |

## Math

- Kimi K3: 74.0 (#13)
- Phi 3 Mini 128k Instruct: 29.2 (#220)

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1493 | 1089 |
| 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% | — |

## Knowledge

- Kimi K3: 63.2 (#19)
- Phi 3 Mini 128k Instruct: 26.3 (#251)

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1520 | 984 |
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |

## Multimodal

- Kimi K3: 38.4 (#58)
- Phi 3 Mini 128k Instruct: —

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |

## Multilingual

- Kimi K3: 56.5 (#20)
- Phi 3 Mini 128k Instruct: 25.4 (#280)

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1466 | 1000 |
| LMArena Chinese | 1528 | 1016 |
| LMArena French | 1488 | 1038 |
| LMArena German | 1474 | 1006 |
| LMArena Japanese | 1492 | 899 |
| LMArena Korean | 1465 | 856 |
| LMArena Russian | 1481 | 1004 |
| LMArena Spanish | 1478 | 1058 |

## Instruction Following

- Kimi K3: 77.8 (#13)
- Phi 3 Mini 128k Instruct: 52.1 (#289)

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1481 | 1023 |

## Long Context

- Kimi K3: 45.8 (#27)
- Phi 3 Mini 128k Instruct: 30.3 (#284)

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1494 | 996 |

## Writing & Preference

- Kimi K3: 76.7 (#4)
- Phi 3 Mini 128k Instruct: 27.3 (#296)

| Benchmark | Kimi K3 | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1476 | 1050 |
| LMArena Creative Writing | 1452 | 1024 |
| LMArena Multi-Turn | 1488 | 989 |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |

## FAQ

### Is Kimi K3 better than Phi 3 Mini 128k Instruct?

Kimi K3 is the stronger model overall, scoring 59.5 to 29.1 on the Noometry Index.

### Is Kimi K3 or Phi 3 Mini 128k Instruct better for coding?

Kimi K3 scores higher on coding benchmarks: 60.6 versus 28.3 in the Noometry coding category.

### How many benchmarks do Kimi K3 and Phi 3 Mini 128k Instruct share?

17 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.