Model comparison
Gemini 1.0 Pro vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 27.3 on the Noometry Index.
Last verified . 16 shared benchmarks.
Google
TencentSummary
- They share 16 benchmarks with published results for both. Gemini 1.0 Pro 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 9.3.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.0 Pro | Hy3 | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 27.3 | 44.2 |
| Released | 2023-12-13 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.13 |
| Output $ / M tokens | — | $0.53 |
| Results tracked | 24 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Gemini 1.0 Pro: 32.2 (#275), Hy3: 46.8 (#63)
| Benchmark | Gemini 1.0 Pro | Hy3 |
|---|---|---|
| LMArena Coding | 1108 | 1464 |
| LMArena WebDev | — | 1508 |
| HumanEval+ | 55.5% | — |
| MBPP+ | 61.4% | — |
Reasoning Hy3 leads
Gemini 1.0 Pro: 17.1 (#296), Hy3: 26.1 (#136)
| Benchmark | Gemini 1.0 Pro | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1109 | 1447 |
| NYT Connections (extended) | — | 41.2% |
| DTBench | 45.9% | — |
| Epoch Capabilities Index | 117.04 | — |
Math Hy3 leads
Gemini 1.0 Pro: 9.3 (#321), Hy3: 40.1 (#93)
| Benchmark | Gemini 1.0 Pro | Hy3 |
|---|---|---|
| LMArena Math | 1132 | 1475 |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 11.2% | — |
Knowledge Hy3 leads
Gemini 1.0 Pro: 15.6 (#291), Hy3: 40.8 (#114)
| Benchmark | Gemini 1.0 Pro | Hy3 |
|---|---|---|
| LMArena Expert | 1059 | 1460 |
| GPQA Diamond | 34% | — |
| MMLU | 70% | — |
Multilingual Hy3 leads
Gemini 1.0 Pro: 33.4 (#252), Hy3: 53.5 (#65)
| Benchmark | Gemini 1.0 Pro | Hy3 |
|---|---|---|
| LMArena Non-English | 1138 | 1426 |
| LMArena Chinese | 1124 | 1493 |
| LMArena French | 1145 | 1461 |
| LMArena German | 1125 | 1439 |
| LMArena Japanese | 1023 | 1392 |
| LMArena Russian | 1186 | 1432 |
| LMArena Spanish | 1119 | 1456 |
| LMArena Korean | — | 1395 |
Instruction Following Hy3 leads
Gemini 1.0 Pro: 57.6 (#267), Hy3: 75.1 (#70)
| Benchmark | Gemini 1.0 Pro | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1114 | 1426 |
Long Context Hy3 leads
Gemini 1.0 Pro: 34.3 (#249), Hy3: 44.1 (#75)
| Benchmark | Gemini 1.0 Pro | Hy3 |
|---|---|---|
| LMArena Longer Query | 1132 | 1442 |
Writing & Preference Hy3 leads
Gemini 1.0 Pro: 36.0 (#264), Hy3: 62.2 (#81)
| Benchmark | Gemini 1.0 Pro | Hy3 |
|---|---|---|
| LMArena Text | 1149 | 1439 |
| LMArena Creative Writing | 1131 | 1402 |
| LMArena Multi-Turn | 1139 | 1436 |
Frequently asked questions
Is Gemini 1.0 Pro better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 27.3 on the Noometry Index.
Is Gemini 1.0 Pro or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 32.2 in the Noometry coding category.
How many benchmarks do Gemini 1.0 Pro and Hy3 share?
16 benchmarks have published results for both models. Gemini 1.0 Pro has 24 scored results on Noometry and Hy3 has 19.