Model comparison
Gemini 2.0 Flash (Feb 2025) vs Hy3
Hy3 is the stronger model overall, scoring 44.2 to 35.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Google
TencentSummary
- They share 17 benchmarks with published results for both. Gemini 2.0 Flash (Feb 2025) scores higher in 0 categories and Hy3 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.8 to 28.4.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.0 Flash (Feb 2025) | Hy3 | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 35.1 | 44.2 |
| Released | 2024-12-06 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.13 |
| Output $ / M tokens | — | $0.53 |
| Results tracked | 54 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Gemini 2.0 Flash (Feb 2025): 28.4 (#315), Hy3: 46.8 (#63)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Coding | 1350 | 1464 |
| SWE-bench Verified (bash only) | 13.5% | — |
| Aider Polyglot | 38.2% | — |
| LMArena WebDev | — | 1508 |
| WeirdML | 25.8% | — |
| BigCodeBench Instruct | 45.9% | — |
| LiveBench Coding | 63.4% | — |
| BigCodeBench Complete | 59.9% | — |
| CadEval | 30% | — |
Agentic & Tool Use Not comparable
Gemini 2.0 Flash (Feb 2025): 28.1 (#92), Hy3: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| TheAgentCompany | 11.4% | — |
Reasoning Hy3 leads
Gemini 2.0 Flash (Feb 2025): 15.2 (#318), Hy3: 26.1 (#136)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1346 | 1447 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31.1% | — |
| Kagi LLM Benchmark | 37.8% | — |
| NYT Connections (extended) | — | 41.2% |
| EnigmaEval | 1.1% | — |
| LiveBench Reasoning | 78.2% | — |
| DTBench | 63.2% | — |
| LiveBench Data Analysis | 69.4% | — |
| Epoch Capabilities Index | 135.36 | — |
| LiveBench | 66.9% | — |
Math Hy3 leads
Gemini 2.0 Flash (Feb 2025): 37.9 (#146), Hy3: 40.1 (#93)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Math | 1352 | 1475 |
| OTIS Mock AIME 2024-2025 | 57.8% | — |
| Omni-MATH | 45.9% | — |
| LiveBench Math | 75.8% | — |
| MATH Level 5 | 82.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Hy3 leads
Gemini 2.0 Flash (Feb 2025): 32.0 (#213), Hy3: 40.8 (#114)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Expert | 1339 | 1460 |
| GPQA Diamond | 64.1% | — |
| Humanity's Last Exam | 6.6% | — |
| MMLU-Pro | 73.7% | — |
| Confabulations | 12.4% | — |
| GPQA (HELM) | 55.6% | — |
| MMLU | 79.7% | — |
Multimodal Not comparable
Gemini 2.0 Flash (Feb 2025): 36.5 (#79), Hy3: —
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Vision | 1158 | — |
| GeoBench | 77% | — |
Multilingual Hy3 leads
Gemini 2.0 Flash (Feb 2025): 47.4 (#149), Hy3: 53.5 (#65)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Non-English | 1342 | 1426 |
| LMArena Chinese | 1373 | 1493 |
| LMArena French | 1391 | 1461 |
| LMArena German | 1353 | 1439 |
| LMArena Japanese | 1294 | 1392 |
| LMArena Korean | 1313 | 1395 |
| LMArena Russian | 1351 | 1432 |
| LMArena Spanish | 1363 | 1456 |
Instruction Following Too close to call
Gemini 2.0 Flash (Feb 2025): 74.4 (#97), Hy3: 75.1 (#70)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1336 | 1426 |
| LiveBench Instruction Following | 85.8% | — |
| IFEval | 84.1% | — |
Long Context Hy3 leads
Gemini 2.0 Flash (Feb 2025): 38.1 (#203), Hy3: 44.1 (#75)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Longer Query | 1344 | 1442 |
| Fiction.LiveBench | 61.1% | — |
Writing & Preference Hy3 leads
Gemini 2.0 Flash (Feb 2025): 49.5 (#190), Hy3: 62.2 (#81)
| Benchmark | Gemini 2.0 Flash (Feb 2025) | Hy3 |
|---|---|---|
| LMArena Text | 1354 | 1439 |
| LMArena Creative Writing | 1340 | 1402 |
| LMArena Multi-Turn | 1350 | 1436 |
| Short-Story Creative Writing | 73.8% | — |
| EQ-Bench Creative Writing | 1128 | — |
| WildBench | 80% | — |
| LiveBench Language | 51.3% | — |
Frequently asked questions
Is Gemini 2.0 Flash (Feb 2025) better than Hy3?
Hy3 is the stronger model overall, scoring 44.2 to 35.1 on the Noometry Index.
Is Gemini 2.0 Flash (Feb 2025) or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.8 versus 28.4 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Flash (Feb 2025) and Hy3 share?
17 benchmarks have published results for both models. Gemini 2.0 Flash (Feb 2025) has 54 scored results on Noometry and Hy3 has 19.