# Claude Sonnet 4.6 vs Hy3 Preview

> Side-by-side benchmark comparison for Claude Sonnet 4.6 and Hy3 Preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-sonnet-4-6-vs-hy3-preview
- Last updated: September 23, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.6

## Quick Verdict

Pick Claude Sonnet 4.6 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

- Claude Sonnet 4.6 leads overall 56.73 to 45.32.
- The clearest category separation is in coding, where the averages are 48.5 for Claude Sonnet 4.6 and 33.3 for Hy3 Preview.
- The biggest single benchmark swing is Gert Labs in Agentic, with scores of 62.92% and 36.91%.
- Hy3 Preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Hy3 Preview also has the larger context window at 256K.

## Model Snapshot

| Property | Claude Sonnet 4.6 | Hy3 Preview |
|----------|----------|----------|
| Creator | Anthropic | Tencent |
| Type | Proprietary | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 256K |
| Overall Score | 56.73 | 45.32 |
| Benchmarks Covered | 26 | 6 |
| Pricing (input/output) | $3.00 / $15.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: 41 (Supported · #44/105)
- Hy3 Preview public-lane score: Coming soon

| Benchmark | Claude Sonnet 4.6 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 59.1% | 54.4% | Claude Sonnet 4.6 |
| OSWorld-Verified | 72.1% | Coming soon | Coming soon |
| Claw-Eval | 67.8% | Coming soon | Coming soon |
| CyberGym | 65.2% | Coming soon | Coming soon |
| Gert Labs | 62.92% | 36.91% | Claude Sonnet 4.6 |
| OSWorld 2.0 | 8.3% | Coming soon | Coming soon |
| JobBench | 36.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 57.3% | Coming soon | Coming soon |
| ApprenticeBench | 2% | Coming soon | Coming soon |

### Coding

- Winner: Directional only
- Claude Sonnet 4.6 public-lane score: 48.5 (Supported · #41/135)
- Hy3 Preview public-lane score: 33.3 (Estimated · #85/135)

| Benchmark | Claude Sonnet 4.6 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 79.6% | 74.4% | Claude Sonnet 4.6 |
| SWE-Rebench | 60.7% | Coming soon | Coming soon |
| React Native Evals | 80.6% | Coming soon | Coming soon |
| Vibe Code Bench | 51.48% | Coming soon | Coming soon |
| cursorBench31 | 48.8% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 24.3% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 82.1% | Coming soon | Coming soon |
| SWE-bench (Vals) | 77.4% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 54.4% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: 67.9 (Unranked · 2 rankable rows)
- Hy3 Preview public-lane score: Coming soon

### Multimodal & Grounded

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: 54.1 (#35/50)
- Hy3 Preview public-lane score: Coming soon

| Benchmark | Claude Sonnet 4.6 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 77.4% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- Claude Sonnet 4.6 public-lane score: 50.8 (Supported · #52/160)
- Hy3 Preview public-lane score: 39.1 (Estimated · #93/160)

| Benchmark | Claude Sonnet 4.6 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 89.9% | 87.2% | Claude Sonnet 4.6 |
| SuperGPQA | 95% | Coming soon | Coming soon |
| MMLU-Pro | 79.2% | Coming soon | Coming soon |
| HLE | 49% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 85.6% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.3% | Coming soon | Coming soon |
| GPQA-D | Coming soon | 87.2% | Coming soon |

### Instruction Following

- Winner: Directional only
- Claude Sonnet 4.6 public-lane score: 46.6 (#88/124)
- Hy3 Preview public-lane score: 46.9 (#86/124)

### Mathematics

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: 48.8 (Unranked · 2 rankable rows)
- Hy3 Preview public-lane score: Coming soon

| Benchmark | Claude Sonnet 4.6 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 32.400% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 8.300% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Claude Sonnet 4.6 or Hy3 Preview?

Claude Sonnet 4.6 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Sonnet 4.6 and Hy3 Preview?

The widest category gap is in coding, where the averages are 48.5 for Claude Sonnet 4.6 and 33.3 for Hy3 Preview.

### How many benchmarks does Claude Sonnet 4.6 cover on BenchLM?

Claude Sonnet 4.6 currently has 26 sourced benchmark scores on BenchLM.

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

Hy3 Preview currently has 6 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Sonnet 4.6 vs Hy3](/compare/claude-sonnet-4-6-vs-hy3)
- [Hy3 Preview vs Hy3](/compare/hy3-vs-hy3-preview)
- [Claude Sonnet 4.6 vs GPT-6 Astra](/compare/claude-sonnet-4-6-vs-gpt-6-astra)
- [Hy3 Preview vs GPT-6 Astra](/compare/gpt-6-astra-vs-hy3-preview)

## Explore More

- [Claude Sonnet 4.6 profile](/models/claude-sonnet-4-6)
- [Hy3 Preview profile](/models/hy3-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)