Model comparison
Gemma 2 9B vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 25.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
TencentSummary
- They share 17 benchmarks with published results for both. Gemma 2 9B scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Hy3 leads 40.8 to 9.7.
Side by side
| Gemma 2 9B | Hy3 | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 25.9 | 44.2 |
| Released | 2024-06-24 | 2026-07-06 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 35 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Gemma 2 9B: 29.4 (#304), Hy3: 46.8 (#63)
| Benchmark | Gemma 2 9B | Hy3 |
|---|---|---|
| LMArena Coding | 1173 | 1464 |
| LMArena WebDev | — | 1508 |
| BigCodeBench Instruct | 34.7% | — |
| LiveBench Coding | 22.5% | — |
| BigCodeBench Complete | 40.6% | — |
Reasoning Hy3 leads
Gemma 2 9B: 15.9 (#309), Hy3: 26.1 (#136)
| Benchmark | Gemma 2 9B | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1171 | 1447 |
| NYT Connections (extended) | — | 41.2% |
| LiveBench Reasoning | 15.2% | — |
| LiveBench Data Analysis | 36.4% | — |
| Epoch Capabilities Index | 119.83 | — |
| LiveBench | 28.7% | — |
| PIQA | 83.7% | — |
Math Hy3 leads
Gemma 2 9B: 9.9 (#318), Hy3: 40.1 (#93)
| Benchmark | Gemma 2 9B | Hy3 |
|---|---|---|
| LMArena Math | 1183 | 1475 |
| OTIS Mock AIME 2024-2025 | 0.6% | — |
| LiveBench Math | 19.8% | — |
| MATH Level 5 | 21% | — |
| GSM8K | 84.9% | — |
Knowledge Hy3 leads
Gemma 2 9B: 9.7 (#305), Hy3: 40.8 (#114)
| Benchmark | Gemma 2 9B | Hy3 |
|---|---|---|
| LMArena Expert | 1147 | 1460 |
| GPQA Diamond | 27.5% | — |
| BoolQ | 85.7% | — |
| MMLU | 72.1% | — |
Multilingual Hy3 leads
Gemma 2 9B: 36.6 (#238), Hy3: 53.5 (#65)
| Benchmark | Gemma 2 9B | Hy3 |
|---|---|---|
| LMArena Non-English | 1188 | 1426 |
| LMArena Chinese | 1185 | 1493 |
| LMArena French | 1190 | 1461 |
| LMArena German | 1186 | 1439 |
| LMArena Japanese | 1144 | 1392 |
| LMArena Korean | 1137 | 1395 |
| LMArena Russian | 1200 | 1432 |
| LMArena Spanish | 1200 | 1456 |
Instruction Following Hy3 leads
Gemma 2 9B: 57.6 (#269), Hy3: 75.1 (#70)
| Benchmark | Gemma 2 9B | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1178 | 1426 |
| LiveBench Instruction Following | 52.6% | — |
Long Context Hy3 leads
Gemma 2 9B: 36.3 (#233), Hy3: 44.1 (#75)
| Benchmark | Gemma 2 9B | Hy3 |
|---|---|---|
| LMArena Longer Query | 1197 | 1442 |
Writing & Preference Hy3 leads
Gemma 2 9B: 32.1 (#281), Hy3: 62.2 (#81)
| Benchmark | Gemma 2 9B | Hy3 |
|---|---|---|
| LMArena Text | 1207 | 1439 |
| LMArena Creative Writing | 1206 | 1402 |
| LMArena Multi-Turn | 1193 | 1436 |
| EQ-Bench Creative Writing | 841 | — |
| LiveBench Language | 25.5% | — |
Frequently asked questions
Is Gemma 2 9B better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 25.9 on the Noometry Index.
Is Gemma 2 9B or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 29.4 in the Noometry coding category.
How many benchmarks do Gemma 2 9B and Hy3 share?
17 benchmarks have published results for both models. Gemma 2 9B has 35 scored results on Noometry and Hy3 has 19.