# Hy3 Preview vs Kimi K2.5

> Side-by-side benchmark comparison for Hy3 Preview and Kimi K2.5 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/hy3-preview-vs-kimi-k2-5
- Last updated: September 23, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.6

## Quick Verdict

Pick Kimi K2.5 if you want the stronger benchmark profile. Hy3 Preview only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Kimi K2.5 leads overall 53.79 to 45.32.
- The clearest category separation is in instruction following, where the averages are 46.9 for Hy3 Preview and 84.4 for Kimi K2.5.
- The biggest single benchmark swing is Gert Labs in Agentic, with scores of 36.91% and 45.88%.
- Hy3 Preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Hy3 Preview | Kimi K2.5 |
|----------|----------|----------|
| Creator | Tencent | Moonshot AI |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 256K | 256K |
| Overall Score | 45.32 | 53.79 |
| Benchmarks Covered | 6 | 45 |
| Pricing (input/output) | $0.00 / $0.00 | $0.60 / $3.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Hy3 Preview public-lane score: Coming soon
- Kimi K2.5 public-lane score: 35.5 (Estimated · #54/105)

| Benchmark | Hy3 Preview | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 54.4% | 50.8% | Hy3 Preview |
| Gert Labs | 36.91% | 45.88% | Kimi K2.5 |
| BrowseComp | Coming soon | 60.6% | Coming soon |
| Claw-Eval | Coming soon | 52.3% | Coming soon |
| QwenClawBench | Coming soon | 54.3% | Coming soon |
| τ³-bench results | Coming soon | 65.7% | Coming soon |
| DeepSearchQA | Coming soon | 77.1% | Coming soon |
| DeepPlanning | Coming soon | 14.4% | Coming soon |
| Toolathlon | Coming soon | 27.8% | Coming soon |
| MCP Atlas | Coming soon | 29.5% | Coming soon |
| MCP-Tasks | Coming soon | 59.1% | Coming soon |
| WideResearch | Coming soon | 72.7% | Coming soon |
| ResearchClawBench | Coming soon | 14.0% | Coming soon |
| JobBench | Coming soon | 8.7% | Coming soon |

### Coding

- Winner: Directional only
- Hy3 Preview public-lane score: 33.3 (Estimated · #85/135)
- Kimi K2.5 public-lane score: 40.9 (Estimated · #58/135)

| Benchmark | Hy3 Preview | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 74.4% | 76.8% | Kimi K2.5 |
| Terminal-Bench 2.0 | 54.4% | Coming soon | Coming soon |
| SWE-bench Verified* | Coming soon | 70.8% | Coming soon |
| LiveCodeBench v6 | Coming soon | 85.0% | Coming soon |
| SWE-bench Pro | Coming soon | 50.7% | Coming soon |
| SWE Multilingual | Coming soon | 73% | Coming soon |
| SWE-Rebench | Coming soon | 58.5% | Coming soon |
| React Native Evals | Coming soon | 77.2% | Coming soon |
| SciCode | Coming soon | 48.7% | Coming soon |

### Reasoning

- Winner: Not comparable
- Hy3 Preview public-lane score: Coming soon
- Kimi K2.5 public-lane score: 54.1 (Unranked · 3 rankable rows)

| Benchmark | Hy3 Preview | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | Coming soon | 61% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Hy3 Preview public-lane score: Coming soon
- Kimi K2.5 public-lane score: 65.8 (#25/50)

| Benchmark | Hy3 Preview | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 78.5% | Coming soon |
| Video-MME | Coming soon | 87.4% | Coming soon |
| MMVU | Coming soon | 80.4% | Coming soon |
| VideoMMMU | Coming soon | 86.6% | Coming soon |

### Knowledge

- Winner: Directional only
- Hy3 Preview public-lane score: 39.1 (Estimated · #93/160)
- Kimi K2.5 public-lane score: 46.4 (Estimated · #68/160)

| Benchmark | Hy3 Preview | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 87.2% | 87.6% | Kimi K2.5 |
| GPQA-D | 87.2% | 87.6% | Kimi K2.5 |
| SuperGPQA | Coming soon | 69.2% | Coming soon |
| MMLU-Pro | Coming soon | 87.1% | Coming soon |
| MMLU-Pro (Arcee) | Coming soon | 87.1% | Coming soon |
| HLE | Coming soon | 30.1% | Coming soon |

### Multilingual

- Winner: Not comparable
- Hy3 Preview public-lane score: Coming soon
- Kimi K2.5 public-lane score: 38.2 (#8/12)

| Benchmark | Hy3 Preview | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 82.3% | Coming soon |
| NOVA-63 | Coming soon | 56.0% | Coming soon |

### Instruction Following

- Winner: Directional only
- Hy3 Preview public-lane score: 46.9 (#86/124)
- Kimi K2.5 public-lane score: 84.4 (#41/124)

| Benchmark | Hy3 Preview | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 93.9% | Coming soon |

### Mathematics

- Winner: Not comparable
- Hy3 Preview public-lane score: Coming soon
- Kimi K2.5 public-lane score: 62.1 (#4/7)

| Benchmark | Hy3 Preview | Kimi K2.5 | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | Coming soon | 96.1% | Coming soon |
| AIME26 | Coming soon | 95.8% | Coming soon |
| AIME25 (Arcee) | Coming soon | 96.3% | Coming soon |
| HMMT Feb 2025 | Coming soon | 95.4% | Coming soon |
| HMMT Nov 2025 | Coming soon | 91.1% | Coming soon |
| HMMT Feb 2026 | Coming soon | 87.1% | Coming soon |
| MMAnswerBench | Coming soon | 81.8% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 27.900% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 4.200% | Coming soon |

## FAQ

### Which is better overall, Hy3 Preview or Kimi K2.5?

Kimi K2.5 is ahead overall on BenchLM right now.

### Where is the biggest gap between Hy3 Preview and Kimi K2.5?

The widest category gap is in instruction following, where the averages are 46.9 for Hy3 Preview and 84.4 for Kimi K2.5.

### How many benchmarks does Hy3 Preview cover on BenchLM?

Hy3 Preview currently has 6 sourced benchmark scores on BenchLM.

### How many benchmarks does Kimi K2.5 cover on BenchLM?

Kimi K2.5 currently has 45 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Hy3 Preview vs Hy3](/compare/hy3-vs-hy3-preview)
- [Kimi K2.5 vs Hy3](/compare/hy3-vs-kimi-k2-5)
- [Hy3 Preview vs Kimi K2.5 (Reasoning)](/compare/hy3-preview-vs-kimi-k2-5-reasoning)
- [Kimi K2.5 vs Kimi K2.5 (Reasoning)](/compare/kimi-k2-5-vs-kimi-k2-5-reasoning)

## Explore More

- [Hy3 Preview profile](/models/hy3-preview)
- [Kimi K2.5 profile](/models/kimi-k2-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)