# Gemma 4 31B vs Hy4

> Side-by-side benchmark comparison for Gemma 4 31B and Hy4 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gemma-4-31b-vs-hy4
- Last updated: November 4, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Gemma 4 31B and Hy4 share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Gemma 4 31B has the lower published output-token price.
- Hy4 has the larger published context window at 1M.

## Model Snapshot

| Property | Gemma 4 31B | Hy4 |
|----------|----------|----------|
| Creator | Google | Tencent |
| Type | Open Weight | Pending |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 1M |
| Independent public score (not head-to-head) | 54.39 | null |
| Benchmarks Covered | 13 | 15 |
| Pricing (input/output) | $0.00 / $0.00 | $0.834 / $2.501 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 31.8 (Estimated · #103/135)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemma 4 31B | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| b3 Agent Security | 83.0% | Coming soon | Coming soon |
| Cyber Misuse Refusal | 84.0% | Coming soon | Coming soon |
| Gert Labs | 35.26% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | Coming soon | 44.40% | Coming soon |
| Terminal-Bench-Science 0.1 | Coming soon | 19.8% | Coming soon |
| HLE w/ tools | Coming soon | 59.1% | Coming soon |
| Agents' Last Exam | Coming soon | 41.0% | Coming soon |
| APEX-Agents | Coming soon | 75.2% | Coming soon |
| AutomationBench | Coming soon | 56.2% | Coming soon |
| OSWorld 2.1 | Coming soon | 78.9% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 34.1 (Supported · #88/156)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemma 4 31B | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| LiveCodeBench v6 | 80.0% | Coming soon | Coming soon |
| SWE-Rebench | 41.6% | Coming soon | Coming soon |
| React Native Evals | 75.2% | Coming soon | Coming soon |
| DeepSWE | Coming soon | 74.9% | Coming soon |
| sweMarathon | Coming soon | 43.8% | Coming soon |
| ProgramBench | Coming soon | 30.0% | Coming soon |
| FrontierCode 2.0 | Coming soon | 31.0% | Coming soon |
| PostTrainBench v1.2 | Coming soon | 35.2% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 65.8 (Unranked · 3 rankable rows)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemma 4 31B | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | 66.4% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 74.5 (#27/58)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemma 4 31B | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| ParseBench | 62.40% | Coming soon | Coming soon |
| MMMU-Pro | 76.9% | 78.6% | Hy4 |
| ZeroBench w/ Python | Coming soon | 55.4% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 44.9 (Estimated · #97/179)
- Hy4 public-lane score: Coming soon

| Benchmark | Gemma 4 31B | Hy4 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 84.3% | Coming soon | Coming soon |
| MMLU-Pro | 85.2% | Coming soon | Coming soon |
| HLE | 26.5% | 59.1% | Hy4 |
| HLE w/o tools | 19.5% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 92.9 (#16/157)
- Hy4 public-lane score: Coming soon

## FAQ

### Is there enough evidence to pick between Gemma 4 31B and Hy4?

Not yet. The models share only 2 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Gemma 4 31B vs Gemma 4 26B A4B](/compare/gemma-4-26b-a4b-vs-gemma-4-31b)
- [Hy4 vs Gemma 4 26B A4B](/compare/gemma-4-26b-a4b-vs-hy4)
- [Gemma 4 31B vs Gemma 4 12B](/compare/gemma-4-12b-vs-gemma-4-31b)
- [Hy4 vs Gemma 4 12B](/compare/gemma-4-12b-vs-hy4)

## Explore More

- [Gemma 4 31B profile](/models/gemma-4-31b)
- [Hy4 profile](/models/hy4)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)