Model comparison
Gemma 3 12B vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 44.6 to 31.8 on the Noometry Index. Gemma 3 12B costs 17× 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 54.5 to 21.0.
- Gemma 3 12B is cheaper at $0.05 / $0.15 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 12B | Hy4 preview | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 31.8 | 44.6 |
| Released | 2025-03-12 | 2026-08-28 |
| Weights | Open | Open |
| Context window | 131K | 1.05M |
| Max output | 8K | 64K |
| Input $ / M tokens | $0.05 | $0.83 |
| Output $ / M tokens | $0.15 | $2.50 |
| Results tracked | 24 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Gemma 3 12B: 31.2 (#276), Hy4 preview: 51.4 (#36)
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1633 |
| SciCode | 17.4% | — |
| LMArena Coding | 1281 | — |
Agentic & Tool Use Not comparable
Gemma 3 12B: 25.3 (#101), Hy4 preview: —
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| Berkeley Function Calling Leaderboard | 30.4% | — |
Reasoning Hy4 preview leads
Gemma 3 12B: 15.2 (#307), Hy4 preview: 30.6 (#75)
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| NYT Connections (extended) | — | 68.2% |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1309 | — |
| DTBench | 48.8% | — |
| LMCA | 4.5% | — |
| Epoch Capabilities Index | 123.49 | — |
Math Hy4 preview leads
Gemma 3 12B: 21.0 (#273), Hy4 preview: 54.5 (#37)
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.7% | — |
| ProofBench | — | 75% |
| LMArena Math | 1307 | — |
Knowledge Not comparable
Gemma 3 12B: 26.5 (#250), Hy4 preview: —
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| GPQA Diamond | 39.5% | — |
| Vectara Hallucination Rate | 4.4% | — |
| LMArena Expert | 1248 | — |
Multimodal Not comparable
Gemma 3 12B: —, Hy4 preview: —
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| MindCube | 46.7% | — |
Multilingual Not comparable
Gemma 3 12B: 45.9 (#160), Hy4 preview: —
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| LMArena Non-English | 1318 | — |
| LMArena German | 1370 | — |
| LMArena Russian | 1335 | — |
Instruction Following Not comparable
Gemma 3 12B: 68.8 (#179), Hy4 preview: —
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 1299 | — |
Long Context Not comparable
Gemma 3 12B: 40.0 (#157), Hy4 preview: —
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 1317 | — |
Writing & Preference Not comparable
Gemma 3 12B: 47.7 (#205), Hy4 preview: —
| Benchmark | Gemma 3 12B | Hy4 preview |
|---|---|---|
| LMArena Text | 1334 | — |
| LMArena Creative Writing | 1331 | — |
| EQ-Bench Creative Writing | 1126 | — |
| LMArena Multi-Turn | 1334 | — |
Frequently asked questions
Is Gemma 3 12B better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 44.6 to 31.8 on the Noometry Index. Gemma 3 12B costs 17× 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 12B or Hy4 preview?
Gemma 3 12B is cheaper. It lists at $0.05 per million input tokens and $0.15 per million output tokens; Hy4 preview lists at $0.83 and $2.50.
Is Gemma 3 12B or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.4 versus 31.2 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 12B and Hy4 preview share?
0 benchmarks have published results for both models. Gemma 3 12B has 24 scored results on Noometry and Hy4 preview has 3.