Model comparison
Gemma 3 4B vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 45.3 to 28.1 on the Noometry Index. Gemma 3 4B costs 25× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Google
TencentSummary
- The widest gap is in math, where Hy4 preview leads 55.7 to 16.8.
- Gemma 3 4B is cheaper at $0.04 / $0.08 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 131K.
Side by side
| Gemma 3 4B | Hy4 preview | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 28.1 | 45.3 |
| Released | 2025-03-12 | 2026-08-28 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 4K | 64K |
| Input $ / M tokens | $0.04 | $0.83 |
| Output $ / M tokens | $0.08 | $2.50 |
| Results tracked | 22 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Gemma 3 4B: 35.9 (#215), Hy4 preview: 51.6 (#38)
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1632 |
| LMArena Coding | 1230 | — |
Agentic & Tool Use Not comparable
Gemma 3 4B: 20.9 (#142), Hy4 preview: —
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 19.6% | — |
Reasoning Hy4 preview leads
Gemma 3 4B: 13.2 (#335), Hy4 preview: 31.9 (#79)
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| Kagi LLM Benchmark | 25.2% | — |
| NYT Connections (extended) | — | 68.2% |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1253 | — |
| DTBench | 50.9% | — |
| LMCA | 2.8% | — |
| Epoch Capabilities Index | 116.02 | — |
Math Hy4 preview leads
Gemma 3 4B: 16.8 (#292), Hy4 preview: 55.7 (#42)
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 7.5% | — |
| ProofBench | — | 75% |
| LMArena Math | 1239 | — |
Knowledge Not comparable
Gemma 3 4B: 11.8 (#299), Hy4 preview: —
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| GPQA Diamond | 23.2% | — |
| Vectara Hallucination Rate | 6.4% | — |
| LMArena Expert | 1223 | — |
Multilingual Not comparable
Gemma 3 4B: 42.5 (#194), Hy4 preview: —
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1273 | — |
| LMArena German | 1281 | — |
| LMArena Russian | 1294 | — |
Instruction Following Not comparable
Gemma 3 4B: 65.2 (#225), Hy4 preview: —
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1239 | — |
Long Context Not comparable
Gemma 3 4B: 38.7 (#194), Hy4 preview: —
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1273 | — |
Writing & Preference Not comparable
Gemma 3 4B: 42.0 (#239), Hy4 preview: —
| Benchmark | Gemma 3 4B | Hy4 preview |
|---|---|---|
| LMArena Text | 1291 | — |
| LMArena Creative Writing | 1271 | — |
| EQ-Bench Creative Writing | 1068 | — |
| LMArena Multi-Turn | 1255 | — |
Frequently asked questions
Is Gemma 3 4B better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 45.3 to 28.1 on the Noometry Index. Gemma 3 4B costs 25× less per token, which makes it the better buy when Hy4 preview's lead doesn't matter for your workload.
Which is cheaper, Gemma 3 4B or Hy4 preview?
Gemma 3 4B is cheaper. It lists at $0.04 per million input tokens and $0.08 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is Gemma 3 4B or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 35.9 in the Noometry coding category.
Which has the bigger context window?
Hy4 preview does, with 1.05M tokens against 131K.
How many benchmarks do Gemma 3 4B and Hy4 preview share?
0 benchmarks have published results for both models. Gemma 3 4B has 22 scored results on Noometry and Hy4 preview has 3.