# Gemini 4 Argon vs Hy4

> Side-by-side benchmark comparison for Gemini 4 Argon and Hy4 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gemini-4-argon-vs-hy4
- Last updated: November 4, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Gemini 4 Argon if you want the stronger benchmark profile. Hy4 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Gemini 4 Argon leads overall 82.28 to 0.
- The biggest single benchmark swing is Terminal-Bench 4.0 in Agentic, with scores of 57.40% and 44.40%.
- Hy4 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Gemini 4 Argon | Hy4 |
|----------|----------|----------|
| Creator | Google | Tencent |
| Type | Proprietary | Pending |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | 82.28 | null |
| Benchmarks Covered | 32 | 15 |
| Pricing (input/output) | $2.00 / $10.00 | $0.834 / $2.501 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Gemini 4 Argon public-lane score: 78.3 (Estimated · #4/135)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemini 4 Argon | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| AutomationBench | 51.3% | 56.2% | Hy4 |
| Finance Agent v2 | 65.4% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | 57.40% | 44.40% | Gemini 4 Argon |
| Agents' Last Exam | 39.5% | 41.0% | Hy4 |
| OSWorld 2.0 | 69.2% | Coming soon | Coming soon |
| CWE-bench v1 | 68.0% | Coming soon | Coming soon |
| Terminal-Bench-Science 0.1 (6x verifier timeout) | 57.6% | Coming soon | Coming soon |
| MazeBench | 12% | Coming soon | Coming soon |
| OSWorld 2.1 Offline | 74.7% | Coming soon | Coming soon |
| ExploitGym | 39.5% | Coming soon | Coming soon |
| Terminal-Bench-Science 0.1 | Coming soon | 19.8% | Coming soon |
| HLE w/ tools | Coming soon | 59.1% | Coming soon |
| APEX-Agents | Coming soon | 75.2% | Coming soon |
| OSWorld 2.1 | Coming soon | 78.9% | Coming soon |

### Coding

- Winner: Not comparable
- Gemini 4 Argon public-lane score: 72.2 (Supported · #6/156)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemini 4 Argon | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| ScarfBench | 75.2% | Coming soon | Coming soon |
| DeepSWE | 77.9% | 74.9% | Gemini 4 Argon |
| FrontierSWE v2 | 55.0% | Coming soon | Coming soon |
| Vibe Code Bench | 91.90% | Coming soon | Coming soon |
| PostTrainBench v1.1 | 45.3% | Coming soon | Coming soon |
| Bug Hunt Bench | 40.7 fixes | Coming soon | Coming soon |
| FrontierCode 2.0 | 26.3% | 31.0% | Hy4 |
| sweMarathon | Coming soon | 43.8% | Coming soon |
| ProgramBench | Coming soon | 30.0% | Coming soon |
| PostTrainBench v1.2 | Coming soon | 35.2% | Coming soon |

### Reasoning

- Winner: Not comparable
- Gemini 4 Argon public-lane score: 86.9 (#3/26)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemini 4 Argon | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| STEMBench | 2.44 | Coming soon | Coming soon |
| Graphwalks BFS 128K | 99.7% | Coming soon | Coming soon |
| GraphWalks BFS 256K–1M | 84.2% | Coming soon | Coming soon |
| ARC-AGI-1 | 98.50% | Coming soon | Coming soon |
| ARC-AGI-2 | 91.3% | Coming soon | Coming soon |
| ARC-AGI-3 | 46.3% | Coming soon | Coming soon |
| ARC-AGI-3 Provider Adapter | 97.30% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Gemini 4 Argon public-lane score: Coming soon
- Hy4 public-lane score: Coming soon

| Benchmark | Gemini 4 Argon | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| ExtractBench Pro | 30% | Coming soon | Coming soon |
| Chartography (no tools) | 71.6% | Coming soon | Coming soon |
| LVBench | 91.7% | Coming soon | Coming soon |
| Blueprint-Bench 2 | 54.4% | Coming soon | Coming soon |
| MMMU-Pro | Coming soon | 78.6% | Coming soon |
| ZeroBench w/ Python | Coming soon | 55.4% | Coming soon |

### Knowledge

- Winner: Not comparable
- Gemini 4 Argon public-lane score: 82.6 (Estimated · #6/179)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemini 4 Argon | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| LABBench2 | 88.8% | Coming soon | Coming soon |
| HLE | Coming soon | 59.1% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Gemini 4 Argon public-lane score: Coming soon
- Hy4 public-lane score: Coming soon

| Benchmark | Gemini 4 Argon | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | 0.7% | Coming soon | Coming soon |

### Mathematics

- Winner: Not comparable
- Gemini 4 Argon public-lane score: 92.8 (Unranked · 2 rankable rows)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemini 4 Argon | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 85.965% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 78.049% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Gemini 4 Argon or Hy4?

Gemini 4 Argon is ahead overall on BenchLM right now.

### How many benchmarks does Gemini 4 Argon cover on BenchLM?

Gemini 4 Argon currently has 32 sourced benchmark scores on BenchLM.

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

Hy4 currently has 15 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Gemini 4 Argon vs Gemini 4 Carbon](/compare/gemini-4-argon-vs-gemini-4-carbon)
- [Hy4 vs Gemini 4 Carbon](/compare/gemini-4-carbon-vs-hy4)
- [Gemini 4 Argon vs Hy4 preview](/compare/gemini-4-argon-vs-hy4-preview)
- [Hy4 vs Hy4 preview](/compare/hy4-vs-hy4-preview)

## Explore More

- [Gemini 4 Argon profile](/models/gemini-4-argon)
- [Hy4 profile](/models/hy4)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)