Model comparison
Gemini 1.5 Pro (May 2024) vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 32.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
TencentSummary
- They share 17 benchmarks with published results for both. Gemini 1.5 Pro (May 2024) 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 25.8.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 1.5 Pro (May 2024) | Hy3 | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 32.1 | 44.2 |
| Released | 2024-02-15 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 45 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Gemini 1.5 Pro (May 2024): 34.2 (#241), Hy3: 46.8 (#63)
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Coding | 1294 | 1464 |
| LMArena WebDev | — | 1508 |
| WeirdML | 22.2% | — |
| BigCodeBench Instruct | 43.8% | — |
| BigCodeBench Complete | 57.5% | — |
| CadEval | 34% | — |
| HumanEval+ | 79.3% | — |
| MBPP+ | 74.6% | — |
Agentic & Tool Use Not comparable
Gemini 1.5 Pro (May 2024): 17.9 (#145), Hy3: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| TheAgentCompany | 3.4% | — |
| Cybench | 7.5% | — |
| BALROG | 21% | — |
Reasoning Hy3 leads
Gemini 1.5 Pro (May 2024): 12.3 (#338), Hy3: 26.1 (#136)
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1296 | 1447 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 27.1% | — |
| NYT Connections (extended) | — | 41.2% |
| DTBench | 59% | — |
| BIG-Bench Hard | 89.2% | — |
| Epoch Capabilities Index | 131.73 | — |
| ForecastBench | 58.4 | — |
Math Hy3 leads
Gemini 1.5 Pro (May 2024): 25.8 (#266), Hy3: 40.1 (#93)
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Math | 1315 | 1475 |
| OTIS Mock AIME 2024-2025 | 23.1% | — |
| Omni-MATH | 36.4% | — |
| MATH Level 5 | 70.4% | — |
Knowledge Hy3 leads
Gemini 1.5 Pro (May 2024): 29.4 (#239), Hy3: 40.8 (#114)
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Expert | 1279 | 1460 |
| GPQA Diamond | 57.2% | — |
| Humanity's Last Exam | 4.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 13.5% | — |
| GPQA (HELM) | 53.4% | — |
| MMLU | 86.9% | — |
Multimodal Not comparable
Gemini 1.5 Pro (May 2024): 36.8 (#77), Hy3: —
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Vision | 1161 | — |
| Video-MME | 75% | — |
Multilingual Hy3 leads
Gemini 1.5 Pro (May 2024): 45.3 (#174), Hy3: 53.5 (#65)
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Non-English | 1312 | 1426 |
| LMArena Chinese | 1331 | 1493 |
| LMArena French | 1302 | 1461 |
| LMArena German | 1286 | 1439 |
| LMArena Japanese | 1292 | 1392 |
| LMArena Korean | 1298 | 1395 |
| LMArena Russian | 1320 | 1432 |
| LMArena Spanish | 1311 | 1456 |
Instruction Following Hy3 leads
Gemini 1.5 Pro (May 2024): 68.6 (#185), Hy3: 75.1 (#70)
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1297 | 1426 |
| IFEval | 83.7% | — |
Long Context Hy3 leads
Gemini 1.5 Pro (May 2024): 39.8 (#169), Hy3: 44.1 (#75)
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Longer Query | 1308 | 1442 |
Writing & Preference Hy3 leads
Gemini 1.5 Pro (May 2024): 52.4 (#172), Hy3: 62.2 (#81)
| Benchmark | Gemini 1.5 Pro (May 2024) | Hy3 |
|---|---|---|
| LMArena Text | 1319 | 1439 |
| LMArena Creative Writing | 1333 | 1402 |
| LMArena Multi-Turn | 1296 | 1436 |
| WildBench | 81.3% | — |
Frequently asked questions
Is Gemini 1.5 Pro (May 2024) better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 32.1 on the Noometry Index.
Is Gemini 1.5 Pro (May 2024) or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 34.2 in the Noometry coding category.
How many benchmarks do Gemini 1.5 Pro (May 2024) and Hy3 share?
17 benchmarks have published results for both models. Gemini 1.5 Pro (May 2024) has 45 scored results on Noometry and Hy3 has 19.