# Hy4 preview vs Kimi K2 (Jul 2025)

> Hy4 preview is the stronger model overall, scoring 45.3 to 41.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy4-preview-vs-kimi-k2
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Hy4 preview leads 55.7 to 42.7.
- Kimi K2 (Jul 2025) is cheaper at $0.57 / $2.30 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| Provider | Tencent | Moonshot AI |
| Noometry Index | 45.3 | 41.2 |
| Rank | 73 | 140 |
| Context | 1.05M | 262K |
| Input $/M | $0.83 | $0.57 |
| Output $/M | $2.50 | $2.30 |
| Weights | Open | Open |

## Coding

- Hy4 preview: 51.6 (#38)
- Kimi K2 (Jul 2025): 42.4 (#102)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| LMArena WebDev | 1632 | — |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| LMArena Coding | — | 1399 |
| ALE-Bench | — | 597.5 |

## Agentic & Tool Use

- Hy4 preview: —
- Kimi K2 (Jul 2025): 32.4 (#64)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| Terminal-Bench | — | 35.7% |
| Berkeley Function Calling Leaderboard | — | 59.1% |
| METR Time Horizons | — | 59.2% |

## Reasoning

- Hy4 preview: 31.9 (#79)
- Kimi K2 (Jul 2025): 23.3 (#179)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| NYT Connections (extended) | 68.2% | — |
| LMArena Hard Prompts | — | 1384 |
| Epoch Capabilities Index | — | 146.01 |
| ForecastBench | — | 60.2 |

## Math

- Hy4 preview: 55.7 (#42)
- Kimi K2 (Jul 2025): 42.7 (#83)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| ProofBench | 75% | — |
| Omni-MATH | — | 65.4% |
| LMArena Math | — | 1397 |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Hy4 preview: —
- Kimi K2 (Jul 2025): 37.3 (#157)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
| LMArena Expert | — | 1365 |

## Multilingual

- Hy4 preview: —
- Kimi K2 (Jul 2025): 49.6 (#130)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | — | 1372 |
| LMArena Chinese | — | 1415 |
| LMArena French | — | 1379 |
| LMArena German | — | 1387 |
| LMArena Japanese | — | 1349 |
| LMArena Korean | — | 1325 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1386 |

## Instruction Following

- Hy4 preview: —
- Kimi K2 (Jul 2025): 71.1 (#156)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| IFEval | — | 85% |
| LMArena Instruction Following | — | 1348 |

## Long Context

- Hy4 preview: —
- Kimi K2 (Jul 2025): 41.2 (#145)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
| LMArena Longer Query | — | 1353 |

## Writing & Preference

- Hy4 preview: —
- Kimi K2 (Jul 2025): 62.3 (#78)

| Benchmark | Hy4 preview | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | — | 1380 |
| LMArena Creative Writing | — | 1350 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
| LMArena Multi-Turn | — | 1371 |

## FAQ

### Is Hy4 preview better than Kimi K2 (Jul 2025)?

Hy4 preview is the stronger model overall, scoring 45.3 to 41.2 on the Noometry Index.

### Which is cheaper, Hy4 preview or Kimi K2 (Jul 2025)?

Kimi K2 (Jul 2025) is cheaper. It lists at $0.57 per million input tokens and $2.30 per million output tokens; Hy4 preview lists at $0.83 and $2.50.

### Is Hy4 preview or Kimi K2 (Jul 2025) better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 262K.

### How many benchmarks do Hy4 preview and Kimi K2 (Jul 2025) share?

0 benchmarks have published results for both models. Hy4 preview has 3 scored results on Noometry and Kimi K2 (Jul 2025) has 42.