# A.X K2 vs Hy4 preview

> Side-by-side benchmark comparison for A.X K2 and Hy4 preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/a-x-k2-vs-hy4-preview
- Last updated: September 10, 2026

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

## Quick Verdict

Pick Hy4 preview if you want the stronger benchmark profile. A.X K2 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Hy4 preview leads overall 61.08 to 49.
- The biggest single benchmark swing is Terminal-Bench 2.1 in Agentic, with scores of 36.0% and 85.4%.
- Hy4 preview also has the larger context window at 1M.

## Model Snapshot

| Property | A.X K2 | Hy4 preview |
|----------|----------|----------|
| Creator | SK Telecom | Tencent |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 1M |
| Overall Score | null | 61.08 |
| Benchmarks Covered | 10 | 28 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- A.X K2 public-lane score: Coming soon
- Hy4 preview public-lane score: 58.2 (Estimated · #30/152)

| Benchmark | A.X K2 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 36.0% | 85.4% | Hy4 preview |
| CyberGym | Coming soon | 78.4% | Coming soon |
| WideResearch | Coming soon | 83.9% | Coming soon |
| DRACO | Coming soon | 77.2% | Coming soon |
| MCP Atlas | Coming soon | 83.7% | Coming soon |
| Toolathlon-Verified | Coming soon | 74.1% | Coming soon |
| APEX-Agents | Coming soon | 37.1% | Coming soon |
| skillsBench | Coming soon | 62.9% | Coming soon |
| JobBench | Coming soon | 61.7% | Coming soon |
| Agents' Last Exam | Coming soon | 22.8% | Coming soon |
| AutomationBench | Coming soon | 32.1% | Coming soon |
| BankerToolBench | Coming soon | 78.6% | Coming soon |
| HLE w/ tools | Coming soon | 55.4% | Coming soon |

### Coding

- Winner: Coming soon
- A.X K2 public-lane score: Coming soon
- Hy4 preview public-lane score: 59.2 (Estimated · #24/151)

| Benchmark | A.X K2 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | 84.0% | Coming soon | Coming soon |
| SciCode | 41% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 36.0% | 85.4% | Hy4 preview |
| SWE-bench Pro | Coming soon | 65.7% | Coming soon |
| SWE Multilingual | Coming soon | 82.9% | Coming soon |
| DeepSWE | Coming soon | 64.3% | Coming soon |
| NL2Repo | Coming soon | 58.9% | Coming soon |
| ProgramBench | Coming soon | 17.5% | Coming soon |
| PostTrain Bench | Coming soon | 35.6% | Coming soon |
| sweMarathon | Coming soon | 31.9% | Coming soon |

### Multimodal & Grounded

- Winner: Coming soon
- A.X K2 public-lane score: Coming soon
- Hy4 preview public-lane score: 84.8 (Unranked · 1 rankable row)

| Benchmark | A.X K2 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | Coming soon | 66.2% | Coming soon |

### Reasoning

- Winner: Coming soon
- A.X K2 public-lane score: Coming soon
- Hy4 preview public-lane score: Coming soon

| Benchmark | A.X K2 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| CritPt | Coming soon | 16.9% | Coming soon |

### Knowledge

- Winner: Coming soon
- A.X K2 public-lane score: Coming soon
- Hy4 preview public-lane score: 56.5 (Estimated · #47/183)

| Benchmark | A.X K2 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| HLE | 27.8% | 55.4% | Hy4 preview |
| GPQA-D | 85.6% | 92.3% | Hy4 preview |
| GPQA | Coming soon | 92.3% | Coming soon |
| HLE w/o tools | Coming soon | 43.4% | Coming soon |

### Instruction Following

- Winner: Coming soon
- A.X K2 public-lane score: Coming soon
- Hy4 preview public-lane score: Coming soon

| Benchmark | A.X K2 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| IFBench | 75.9% | Coming soon | Coming soon |

### Mathematics

- Winner: Coming soon
- A.X K2 public-lane score: Coming soon
- Hy4 preview public-lane score: Coming soon

| Benchmark | A.X K2 | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 97.1% | Coming soon | Coming soon |
| Apex | 45.8% | 74.2% | Hy4 preview |
| Apex Shortlist | 88.6% | Coming soon | Coming soon |

## FAQ

### Which is better overall, A.X K2 or Hy4 preview?

Hy4 preview is ahead overall on BenchLM right now.

### How many benchmarks does A.X K2 cover on BenchLM?

A.X K2 currently has 10 sourced benchmark scores on BenchLM.

### How many benchmarks does Hy4 preview cover on BenchLM?

Hy4 preview currently has 28 sourced benchmark scores on BenchLM.

## Related Comparisons

- [A.X K2 vs A.X series](/compare/a-x-k2-vs-skt-ax)
- [Hy4 preview vs A.X series](/compare/hy4-preview-vs-skt-ax)
- [A.X K2 vs Claude Fable 5.1](/compare/a-x-k2-vs-claude-fable-5-1)
- [Hy4 preview vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-hy4-preview)

## Explore More

- [A.X K2 profile](/models/a-x-k2)
- [Hy4 preview profile](/models/hy4-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)