# Kimi K2 (Jul 2025) vs Phi 3 Small 8k Instruct

> Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 28.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 8 categories and Phi 3 Small 8k Instruct 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 31.3.

## Snapshot

| | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Moonshot AI | Microsoft |
| Noometry Index | 40.9 | 28.8 |
| Rank | 134 | 310 |
| Context | 262K | — |
| Input $/M | $0.57 | — |
| Output $/M | $2.30 | — |
| Weights | Open | Open |

## Coding

- Kimi K2 (Jul 2025): 43.1 (#83)
- Phi 3 Small 8k Instruct: 27.4 (#313)

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1399 | 1102 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| LiveBench Coding | — | 20.3% |
| ALE-Bench | 597.5 | — |

## Agentic & Tool Use

- Kimi K2 (Jul 2025): 32.2 (#59)
- Phi 3 Small 8k Instruct: —

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |

## Reasoning

- Kimi K2 (Jul 2025): 22.7 (#173)
- Phi 3 Small 8k Instruct: 14.2 (#319)

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1100 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 146.02 | — |
| ForecastBench | 60.2 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- Kimi K2 (Jul 2025): 40.1 (#81)
- Phi 3 Small 8k Instruct: 25.4 (#247)

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1396 | 1151 |
| Omni-MATH | 65.4% | — |
| LiveBench Math | — | 17.6% |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Kimi K2 (Jul 2025): 36.9 (#153)
- Phi 3 Small 8k Instruct: 28.5 (#237)

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1363 | 1067 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- Kimi K2 (Jul 2025): 49.8 (#125)
- Phi 3 Small 8k Instruct: 28.6 (#267)

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1372 | 1058 |
| LMArena Chinese | 1416 | 1061 |
| LMArena French | 1379 | 1134 |
| LMArena German | 1386 | 1080 |
| LMArena Japanese | 1349 | 966 |
| LMArena Korean | 1324 | 894 |
| LMArena Russian | 1384 | 1111 |
| LMArena Spanish | 1383 | 1111 |

## Instruction Following

- Kimi K2 (Jul 2025): 71.3 (#151)
- Phi 3 Small 8k Instruct: 52.2 (#287)

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1347 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
| IFEval | 85% | — |

## Long Context

- Kimi K2 (Jul 2025): 41.2 (#140)
- Phi 3 Small 8k Instruct: 33.0 (#262)

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1353 | 1088 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |

## Writing & Preference

- Kimi K2 (Jul 2025): 62.5 (#76)
- Phi 3 Small 8k Instruct: 31.3 (#279)

| Benchmark | Kimi K2 (Jul 2025) | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1380 | 1110 |
| LMArena Creative Writing | 1349 | 1083 |
| LMArena Multi-Turn | 1371 | 1068 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
| LiveBench Language | — | 12.9% |

## FAQ

### Is Kimi K2 (Jul 2025) better than Phi 3 Small 8k Instruct?

Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 28.8 on the Noometry Index.

### Is Kimi K2 (Jul 2025) or Phi 3 Small 8k Instruct better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 27.4 in the Noometry coding category.

### How many benchmarks do Kimi K2 (Jul 2025) and Phi 3 Small 8k Instruct share?

17 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Phi 3 Small 8k Instruct has 32.