Model comparison
Gemma 7B vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 30.0 on the Noometry Index.
Last verified . 13 shared benchmarks.
Google
TencentSummary
- They share 13 benchmarks with published results for both. Gemma 7B scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Hy3 leads 62.2 to 27.1.
Side by side
| Gemma 7B | Hy3 | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 30.0 | 44.2 |
| Released | 2024-02-21 | 2026-07-06 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 27 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Gemma 7B: 30.5 (#294), Hy3: 46.8 (#63)
| Benchmark | Gemma 7B | Hy3 |
|---|---|---|
| LMArena Coding | 1048 | 1464 |
| LMArena WebDev | — | 1508 |
| HumanEval+ | 28.7% | — |
| MBPP+ | 43.4% | — |
Reasoning Hy3 leads
Gemma 7B: 19.9 (#249), Hy3: 26.1 (#136)
| Benchmark | Gemma 7B | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1042 | 1447 |
| NYT Connections (extended) | — | 41.2% |
| Adversarial NLI | 48.7% | — |
| BIG-Bench Hard | 55.1% | — |
| Epoch Capabilities Index | 111.99 | — |
| HellaSwag | 82.2% | — |
| PIQA | 81.2% | — |
| WinoGrande | 79% | — |
Math Hy3 leads
Gemma 7B: 31.2 (#228), Hy3: 40.1 (#93)
| Benchmark | Gemma 7B | Hy3 |
|---|---|---|
| LMArena Math | 1066 | 1475 |
| GSM8K | 46.4% | — |
Knowledge Hy3 leads
Gemma 7B: 27.3 (#252), Hy3: 40.8 (#114)
| Benchmark | Gemma 7B | Hy3 |
|---|---|---|
| LMArena Expert | 1001 | 1460 |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 83.2% | — |
| MMLU | 66.1% | — |
| OpenBookQA | 78.6% | — |
| TriviaQA | 72.3% | — |
Multilingual Hy3 leads
Gemma 7B: 25.1 (#287), Hy3: 53.5 (#65)
| Benchmark | Gemma 7B | Hy3 |
|---|---|---|
| LMArena Non-English | 999 | 1426 |
| LMArena Chinese | 1035 | 1493 |
| LMArena French | 1025 | 1461 |
| LMArena Russian | 993 | 1432 |
| LMArena German | — | 1439 |
| LMArena Japanese | — | 1392 |
| LMArena Korean | — | 1395 |
| LMArena Spanish | — | 1456 |
Instruction Following Hy3 leads
Gemma 7B: 51.5 (#295), Hy3: 75.1 (#70)
| Benchmark | Gemma 7B | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1017 | 1426 |
Long Context Hy3 leads
Gemma 7B: 31.1 (#282), Hy3: 44.1 (#75)
| Benchmark | Gemma 7B | Hy3 |
|---|---|---|
| LMArena Longer Query | 1022 | 1442 |
Writing & Preference Hy3 leads
Gemma 7B: 27.1 (#302), Hy3: 62.2 (#81)
| Benchmark | Gemma 7B | Hy3 |
|---|---|---|
| LMArena Text | 1056 | 1439 |
| LMArena Creative Writing | 1024 | 1402 |
| LMArena Multi-Turn | 963 | 1436 |
Frequently asked questions
Is Gemma 7B better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 30.0 on the Noometry Index.
Is Gemma 7B or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 30.5 in the Noometry coding category.
How many benchmarks do Gemma 7B and Hy3 share?
13 benchmarks have published results for both models. Gemma 7B has 27 scored results on Noometry and Hy3 has 19.