# Gemma 4 31B vs Hy4 preview

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

- Canonical page: https://benchlm.ai/compare/gemma-4-31b-vs-hy4-preview
- Last updated: October 13, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Gemma 4 31B and Hy4 preview share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Hy4 preview has the larger published context window at 1M.

## Model Snapshot

| Property | Gemma 4 31B | Hy4 preview |
|----------|----------|----------|
| Creator | Google | Tencent |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 256K | 1M |
| Independent public score (not head-to-head) | 39.81 | 60.86 |
| Benchmarks Covered | 10 | 30 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 19.4 (Estimated · #103/123)
- Hy4 preview public-lane score: 54.5 (Estimated · #37/123)

| Benchmark | Gemma 4 31B | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| Gert Labs | 35.26% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 85.4% | Coming soon |
| 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 |
| Terminal-Bench 2.1 (Vals) | Coming soon | 55.1% | Coming soon |
| CWE-bench v1 | Coming soon | 53.0% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 32.2 (Supported · #88/148)
- Hy4 preview public-lane score: 57.1 (Supported · #26/148)

| Benchmark | Gemma 4 31B | Hy4 preview | 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 |
| Terminal-Bench 2.1 | Coming soon | 85.4% | Coming soon |
| 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 |

### Reasoning

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 66.6 (Unranked · 3 rankable rows)
- Hy4 preview public-lane score: Coming soon

| Benchmark | Gemma 4 31B | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| MRCRv2 | 66.4% | Coming soon | Coming soon |
| CritPt | Coming soon | 16.9% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 74.3 (#26/54)
- Hy4 preview public-lane score: 88.3 (Unranked · 1 rankable row)

| Benchmark | Gemma 4 31B | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 76.9% | Coming soon | Coming soon |
| OfficeQA Pro | Coming soon | 66.2% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 40.8 (Supported · #111/180)
- Hy4 preview public-lane score: 63.6 (Estimated · #39/180)

| Benchmark | Gemma 4 31B | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 84.3% | 92.3% | Hy4 preview |
| MMLU-Pro | 85.2% | Coming soon | Coming soon |
| HLE | 26.5% | 55.4% | Hy4 preview |
| HLE w/o tools | 19.5% | 43.4% | Hy4 preview |
| GPQA-D | Coming soon | 92.3% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: 92.9 (#15/127)
- Hy4 preview public-lane score: Coming soon

### Mathematics

- Winner: Insufficient shared evidence
- Gemma 4 31B public-lane score: Coming soon
- Hy4 preview public-lane score: Coming soon

| Benchmark | Gemma 4 31B | Hy4 preview | Winner |
|-----------|-----------|-----------|--------|
| Apex | Coming soon | 74.2% | Coming soon |

## FAQ

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

Not yet. The models share only 3 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 preview vs Gemma 4 26B A4B](/compare/gemma-4-26b-a4b-vs-hy4-preview)
- [Gemma 4 31B vs Gemma 4 12B](/compare/gemma-4-12b-vs-gemma-4-31b)
- [Hy4 preview vs Gemma 4 12B](/compare/gemma-4-12b-vs-hy4-preview)

## Explore More

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