Model comparison
Gemma 2B vs Hy4 preview
Hy4 preview is the stronger model overall, scoring 45.3 to 29.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in math, where Hy4 preview leads 55.7 to 30.0.
Side by side
| Gemma 2B | Hy4 preview | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 29.6 | 45.3 |
| Released | 2024-02-21 | 2026-08-28 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.83 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 23 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy4 preview leads
Gemma 2B: 29.4 (#305), Hy4 preview: 51.6 (#38)
| Benchmark | Gemma 2B | Hy4 preview |
|---|---|---|
| LMArena WebDev | — | 1632 |
| LMArena Coding | 1010 | — |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Hy4 preview leads
Gemma 2B: 18.8 (#275), Hy4 preview: 31.9 (#79)
| Benchmark | Gemma 2B | Hy4 preview |
|---|---|---|
| NYT Connections (extended) | — | 68.2% |
| LMArena Hard Prompts | 989 | — |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Hy4 preview leads
Gemma 2B: 30.0 (#239), Hy4 preview: 55.7 (#42)
| Benchmark | Gemma 2B | Hy4 preview |
|---|---|---|
| ProofBench | — | 75% |
| LMArena Math | 1009 | — |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Hy4 preview: —
| Benchmark | Gemma 2B | Hy4 preview |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Not comparable
Gemma 2B: 23.0 (#294), Hy4 preview: —
| Benchmark | Gemma 2B | Hy4 preview |
|---|---|---|
| LMArena Non-English | 958 | — |
| LMArena Chinese | 986 | — |
| LMArena Russian | 937 | — |
Instruction Following Not comparable
Gemma 2B: 48.5 (#302), Hy4 preview: —
| Benchmark | Gemma 2B | Hy4 preview |
|---|---|---|
| LMArena Instruction Following | 970 | — |
Long Context Not comparable
Gemma 2B: 29.9 (#291), Hy4 preview: —
| Benchmark | Gemma 2B | Hy4 preview |
|---|---|---|
| LMArena Longer Query | 981 | — |
Writing & Preference Not comparable
Gemma 2B: 24.0 (#308), Hy4 preview: —
| Benchmark | Gemma 2B | Hy4 preview |
|---|---|---|
| LMArena Text | 1002 | — |
| LMArena Creative Writing | 987 | — |
| LMArena Multi-Turn | 945 | — |
Frequently asked questions
Is Gemma 2B better than Hy4 preview?
Hy4 preview is the stronger model overall, scoring 45.3 to 29.6 on the Noometry Index.
Is Gemma 2B or Hy4 preview better for coding?
Hy4 preview scores higher on coding benchmarks: 51.6 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2B and Hy4 preview share?
0 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Hy4 preview has 3.