# Claude Opus 4.8 vs Hy3 Preview

> Side-by-side benchmark comparison for Claude Opus 4.8 and Hy3 Preview across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-opus-4-8-vs-hy3-preview
- Last updated: October 10, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Claude Opus 4.8 leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- Claude Opus 4.8 has the higher overall point estimate 69.12 to 52.5. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in coding, where the averages are 60.8 for Claude Opus 4.8 and 31 for Hy3 Preview.
- The biggest single benchmark swing is Gert Labs in Agentic, with scores of 72.97% and 36.91%.
- Hy3 Preview is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Claude Opus 4.8 also has the larger context window at 1M.

## Model Snapshot

| Property | Claude Opus 4.8 | Hy3 Preview |
|----------|----------|----------|
| Creator | Anthropic | Tencent |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 256K |
| Overall Score | 69.12 | 52.5 |
| Benchmarks Covered | 40 | 6 |
| Pricing (input/output) | $5.00 / $25.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Claude Opus 4.8 public-lane score: 61.6 (Supported · #20/123)
- Hy3 Preview public-lane score: Coming soon

| Benchmark | Claude Opus 4.8 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 3.0 | 21.1% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 74.6% | Coming soon | Coming soon |
| BrowseComp | 84.3% | Coming soon | Coming soon |
| DeepSearchQA | 93.1% | Coming soon | Coming soon |
| OSWorld-Verified | 83.4% | Coming soon | Coming soon |
| Finance Agent v2 | 53.9% | Coming soon | Coming soon |
| MCP Atlas | 82.2% | Coming soon | Coming soon |
| Toolathlon | 59.9% | Coming soon | Coming soon |
| Gert Labs | 72.97% | 36.91% | Claude Opus 4.8 |
| ResearchClawBench | 21.1% | Coming soon | Coming soon |
| OSWorld 2.0 | 20.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 71.9% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 54.4% | Coming soon |

### Coding

- Winner: Directional only
- Claude Opus 4.8 public-lane score: 60.8 (Supported · #19/146)
- Hy3 Preview public-lane score: 31 (Estimated · #92/146)

| Benchmark | Claude Opus 4.8 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 88.6% | 74.4% | Claude Opus 4.8 |
| SWE-bench Pro | 69.2% | Coming soon | Coming soon |
| SWE Multilingual | 84.4% | Coming soon | Coming soon |
| SWE Multimodal | 38.4% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 74.6% | Coming soon | Coming soon |
| cursorBench31 | 58.4% | Coming soon | Coming soon |
| CursorBench 3.2 | 62.3% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 46.5% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.8% | Coming soon | Coming soon |
| SWE-bench (Vals) | 88.6% | Coming soon | Coming soon |
| PostTrainBench v1.1 | 32.9% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 54.4% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Opus 4.8 public-lane score: 62.9 (#24/28)
- Hy3 Preview public-lane score: Coming soon

| Benchmark | Claude Opus 4.8 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 72.1% | Coming soon | Coming soon |
| ARC-AGI-3 | 1.5% | Coming soon | Coming soon |
| ARC-AGI-1 | 92.50% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Claude Opus 4.8 public-lane score: 91.2 (#5/54)
- Hy3 Preview public-lane score: Coming soon

| Benchmark | Claude Opus 4.8 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | 66.2% | Coming soon | Coming soon |
| ScreenSpot Pro | 87.9% | Coming soon | Coming soon |
| CharXiv | 89.9% | Coming soon | Coming soon |
| CharXiv w/o tools | 80.5% | Coming soon | Coming soon |

### Knowledge

- Winner: Directional only
- Claude Opus 4.8 public-lane score: 70.7 (Supported · #14/177)
- Hy3 Preview public-lane score: 46.5 (Estimated · #87/177)

| Benchmark | Claude Opus 4.8 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 93.6% | 87.2% | Claude Opus 4.8 |
| GPQA-D | 93.6% | 87.2% | Claude Opus 4.8 |
| HLE | 57.9% | Coming soon | Coming soon |
| HLE w/o tools | 49.8% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 92.4% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 89.6% | Coming soon | Coming soon |

### Multilingual

- Winner: Not comparable
- Claude Opus 4.8 public-lane score: Coming soon
- Hy3 Preview public-lane score: Coming soon

| Benchmark | Claude Opus 4.8 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| INCLUDE | 87.6% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- Claude Opus 4.8 public-lane score: 75.4 (#61/127)
- Hy3 Preview public-lane score: 48.4 (#86/127)

### Mathematics

- Winner: Not comparable
- Claude Opus 4.8 public-lane score: 65.7 (#2/7)
- Hy3 Preview public-lane score: Coming soon

| Benchmark | Claude Opus 4.8 | Hy3 Preview | Winner |
|-----------|-----------|-----------|--------|
| USAMO 2026 | 96.7% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 47.241% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 31.250% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Claude Opus 4.8 or Hy3 Preview?

Claude Opus 4.8 has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Claude Opus 4.8 and Hy3 Preview?

The widest category gap is in coding, where the averages are 60.8 for Claude Opus 4.8 and 31 for Hy3 Preview.

### How many benchmarks does Claude Opus 4.8 cover on BenchLM?

Claude Opus 4.8 currently has 40 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 Opus 4.8 vs Hy3](/compare/claude-opus-4-8-vs-hy3)
- [Hy3 Preview vs Hy3](/compare/hy3-vs-hy3-preview)
- [Claude Opus 4.8 vs Claude Opus 5.5](/compare/claude-opus-4-8-vs-claude-opus-5-5)
- [Hy3 Preview vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-hy3-preview)

## Explore More

- [Claude Opus 4.8 profile](/models/claude-opus-4-8)
- [Hy3 Preview profile](/models/hy3-preview)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)