Model comparison
Gemini 2.0 Flash-Lite vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 37.8 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
TencentSummary
- They share 17 benchmarks with published results for both. Gemini 2.0 Flash-Lite 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 51.7.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash-Lite | Hy3 | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 37.8 | 44.2 |
| Released | 2025-02-05 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.0825 |
| Output $ / M tokens | — | $0.33 |
| Results tracked | 32 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Gemini 2.0 Flash-Lite: 37.9 (#185), Hy3: 46.8 (#63)
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Coding | 1322 | 1464 |
| LMArena WebDev | — | 1508 |
| LiveBench Coding | 47.1% | — |
Reasoning Hy3 leads
Gemini 2.0 Flash-Lite: 22.0 (#210), Hy3: 26.1 (#136)
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1324 | 1447 |
| NYT Connections (extended) | — | 41.2% |
| LiveBench Reasoning | 50.1% | — |
| DTBench | 52.5% | — |
| LiveBench Data Analysis | 65.5% | — |
| ForecastBench | 57.1 | — |
| LiveBench | 54.3% | — |
Math Hy3 leads
Gemini 2.0 Flash-Lite: 34.1 (#196), Hy3: 40.1 (#93)
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Math | 1309 | 1475 |
| Omni-MATH | 37.4% | — |
| LiveBench Math | 58.1% | — |
Knowledge Hy3 leads
Gemini 2.0 Flash-Lite: 35.0 (#189), Hy3: 40.8 (#114)
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Expert | 1305 | 1460 |
| MMLU-Pro | 72% | — |
| GPQA (HELM) | 50% | — |
Multimodal Not comparable
Gemini 2.0 Flash-Lite: 31.2 (#109), Hy3: —
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Vision | 1100 | — |
Multilingual Hy3 leads
Gemini 2.0 Flash-Lite: 46.0 (#161), Hy3: 53.5 (#65)
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Non-English | 1323 | 1426 |
| LMArena Chinese | 1339 | 1493 |
| LMArena French | 1347 | 1461 |
| LMArena German | 1306 | 1439 |
| LMArena Japanese | 1301 | 1392 |
| LMArena Korean | 1325 | 1395 |
| LMArena Russian | 1328 | 1432 |
| LMArena Spanish | 1313 | 1456 |
Instruction Following Hy3 leads
Gemini 2.0 Flash-Lite: 70.4 (#163), Hy3: 75.1 (#70)
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1305 | 1426 |
| LiveBench Instruction Following | 78.3% | — |
| IFEval | 82.4% | — |
Long Context Hy3 leads
Gemini 2.0 Flash-Lite: 40.1 (#160), Hy3: 44.1 (#75)
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Longer Query | 1320 | 1442 |
Writing & Preference Hy3 leads
Gemini 2.0 Flash-Lite: 51.7 (#177), Hy3: 62.2 (#81)
| Benchmark | Gemini 2.0 Flash-Lite | Hy3 |
|---|---|---|
| LMArena Text | 1330 | 1439 |
| LMArena Creative Writing | 1319 | 1402 |
| LMArena Multi-Turn | 1307 | 1436 |
| WildBench | 79% | — |
| LiveBench Language | 34.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash-Lite better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 37.8 on the Noometry Index.
Is Gemini 2.0 Flash-Lite or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 37.9 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash-Lite and Hy3 share?
17 benchmarks have published results for both models. Gemini 2.0 Flash-Lite has 32 scored results on Noometry and Hy3 has 19.