Model comparison
Gemma 2 27B vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 29.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
TencentSummary
- They share 17 benchmarks with published results for both. Gemma 2 27B scores higher in 0 categories and Hy3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy3 leads 40.1 to 10.7.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.65 / $0.65 for Gemma 2 27B.
- Hy3 accepts more context: 262K tokens versus 8K.
Side by side
| Gemma 2 27B | Hy3 | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 29.4 | 44.2 |
| Released | 2024-06-24 | 2026-07-06 |
| Weights | Open | Open |
| Context window | 8K | 262K |
| Max output | 2K | 128K |
| Input $ / M tokens | $0.65 | $0.13 |
| Output $ / M tokens | $0.65 | $0.53 |
| Results tracked | 34 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Gemma 2 27B: 34.1 (#246), Hy3: 46.8 (#63)
| Benchmark | Gemma 2 27B | Hy3 |
|---|---|---|
| LMArena Coding | 1211 | 1464 |
| LMArena WebDev | — | 1508 |
| BigCodeBench Instruct | 42.8% | — |
| LiveBench Coding | 36% | — |
| BigCodeBench Complete | 52.5% | — |
Reasoning Hy3 leads
Gemma 2 27B: 15.3 (#315), Hy3: 26.1 (#136)
| Benchmark | Gemma 2 27B | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1198 | 1447 |
| NYT Connections (extended) | — | 41.2% |
| LiveBench Reasoning | 28.1% | — |
| DTBench | 48% | — |
| LiveBench Data Analysis | 47.9% | — |
| LMCA | 7.1% | — |
| Epoch Capabilities Index | 122.08 | — |
| LiveBench | 38.2% | — |
Math Hy3 leads
Gemma 2 27B: 10.7 (#311), Hy3: 40.1 (#93)
| Benchmark | Gemma 2 27B | Hy3 |
|---|---|---|
| LMArena Math | 1212 | 1475 |
| OTIS Mock AIME 2024-2025 | 1.4% | — |
| LiveBench Math | 26.5% | — |
| MATH Level 5 | 27.9% | — |
Knowledge Hy3 leads
Gemma 2 27B: 19.0 (#280), Hy3: 40.8 (#114)
| Benchmark | Gemma 2 27B | Hy3 |
|---|---|---|
| LMArena Expert | 1172 | 1460 |
| GPQA Diamond | 36.5% | — |
| Confabulations | 27.1% | — |
| MMLU | 75.7% | — |
Multilingual Hy3 leads
Gemma 2 27B: 38.6 (#226), Hy3: 53.5 (#65)
| Benchmark | Gemma 2 27B | Hy3 |
|---|---|---|
| LMArena Non-English | 1217 | 1426 |
| LMArena Chinese | 1221 | 1493 |
| LMArena French | 1247 | 1461 |
| LMArena German | 1209 | 1439 |
| LMArena Japanese | 1175 | 1392 |
| LMArena Korean | 1174 | 1395 |
| LMArena Russian | 1234 | 1432 |
| LMArena Spanish | 1228 | 1456 |
Instruction Following Hy3 leads
Gemma 2 27B: 60.5 (#249), Hy3: 75.1 (#70)
| Benchmark | Gemma 2 27B | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1206 | 1426 |
| LiveBench Instruction Following | 58.1% | — |
Long Context Hy3 leads
Gemma 2 27B: 37.3 (#218), Hy3: 44.1 (#75)
| Benchmark | Gemma 2 27B | Hy3 |
|---|---|---|
| LMArena Longer Query | 1231 | 1442 |
Writing & Preference Hy3 leads
Gemma 2 27B: 44.2 (#225), Hy3: 62.2 (#81)
| Benchmark | Gemma 2 27B | Hy3 |
|---|---|---|
| LMArena Text | 1231 | 1439 |
| LMArena Creative Writing | 1241 | 1402 |
| LMArena Multi-Turn | 1224 | 1436 |
| LiveBench Language | 32.6% | — |
Frequently asked questions
Is Gemma 2 27B better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 29.4 on the Noometry Index.
Which is cheaper, Gemma 2 27B or Hy3?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Gemma 2 27B lists at $0.65 and $0.65.
Is Gemma 2 27B or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Hy3 does, with 262K tokens against 8K.
How many benchmarks do Gemma 2 27B and Hy3 share?
17 benchmarks have published results for both models. Gemma 2 27B has 34 scored results on Noometry and Hy3 has 19.