# Gemma 3 1B vs Hy4 preview

> Hy4 preview is the stronger model overall, scoring 45.3 to 21.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-1b-vs-hy4-preview
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Summary

- The widest gap is in math, where Hy4 preview leads 55.7 to 10.2.

## Snapshot

| | Gemma 3 1B | Hy4 preview |
|---|---|---|
| Provider | Google | Tencent |
| Noometry Index | 21.1 | 45.3 |
| Rank | 353 | 73 |
| Context | — | 1.05M |
| Input $/M | — | $0.83 |
| Output $/M | — | $2.50 |
| Weights | Open | Open |

## Coding

- Gemma 3 1B: —
- Hy4 preview: 51.6 (#38)

| Benchmark | Gemma 3 1B | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1632 |

## Agentic & Tool Use

- Gemma 3 1B: 13.7 (#152)
- Hy4 preview: —

| Benchmark | Gemma 3 1B | Hy4 preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 7.2% | — |

## Reasoning

- Gemma 3 1B: 19.2 (#264)
- Hy4 preview: 31.9 (#79)

| Benchmark | Gemma 3 1B | Hy4 preview |
|---|---|---|
| NYT Connections (extended) | — | 68.2% |
| Chess Puzzles | 0% | — |

## Math

- Gemma 3 1B: 10.2 (#316)
- Hy4 preview: 55.7 (#42)

| Benchmark | Gemma 3 1B | Hy4 preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| ProofBench | — | 75% |

## Knowledge

- Gemma 3 1B: 7.0 (#314)
- Hy4 preview: —

| Benchmark | Gemma 3 1B | Hy4 preview |
|---|---|---|
| GPQA Diamond | 19.9% | — |

## FAQ

### Is Gemma 3 1B better than Hy4 preview?

Hy4 preview is the stronger model overall, scoring 45.3 to 21.1 on the Noometry Index.

### How many benchmarks do Gemma 3 1B and Hy4 preview share?

0 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and Hy4 preview has 3.