Model comparison
Gemini 2.5 Flash vs Hy3
Hy3 is the stronger model overall, scoring 43.6 to 39.0 on the Noometry Index.
Last verified . 15 shared benchmarks.
Google
TencentSummary
- They share 15 benchmarks with published results for both. Gemini 2.5 Flash scores higher in 3 categories and Hy3 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where Hy3 leads 46.6 to 35.5.
- Hy3 is cheaper at $0.13 / $0.53 per million input/output tokens, against $0.30 / $2.50 for Gemini 2.5 Flash.
- Gemini 2.5 Flash accepts more context: 1.05M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.
Side by side
| Gemini 2.5 Flash | Hy3 | |
|---|---|---|
| Provider | Tencent | |
| Noometry Index | 39.0 | 43.6 |
| Released | 2025-04-17 | 2026-07-06 |
| Weights | Proprietary | Open |
| Context window | 1.05M | 262K |
| Max output | 66K | 128K |
| Input $ / M tokens | $0.30 | $0.13 |
| Output $ / M tokens | $2.50 | $0.53 |
| Results tracked | 54 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Hy3 leads
Gemini 2.5 Flash: 35.5 (#210), Hy3: 46.6 (#60)
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Coding | 1424 | 1465 |
| SWE-bench Verified (bash only) | 28.7% | — |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1509 |
| WeirdML | 41.9% | — |
| ALE-Bench | 661.88 | — |
Agentic & Tool Use Not comparable
Gemini 2.5 Flash: 30.6 (#67), Hy3: —
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| Terminal-Bench | 17.1% | — |
| Berkeley Function Calling Leaderboard | 56.2% | — |
| TheAgentCompany | 41.1% | — |
| BALROG | 33.5% | — |
| Vending-Bench 2 | 548.84 | — |
Reasoning Hy3 leads
Gemini 2.5 Flash: 18.2 (#271), Hy3: 25.0 (#134)
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1449 |
| ARC-AGI-2 | 2.5% | — |
| SimpleBench | 41.2% | — |
| Kagi LLM Benchmark | 56.8% | — |
| NYT Connections (extended) | — | 41.2% |
| ARC-AGI-1 | 33.3% | — |
| CritPt | 1.1% | — |
| EnigmaEval | 2.7% | — |
| DTBench | 76.5% | — |
| LMCA | 27.5% | — |
| Epoch Capabilities Index | 143.04 | — |
| ForecastBench | 60.6 | — |
Math Too close to call
Gemini 2.5 Flash: 38.1 (#87), Hy3: 37.4 (#98)
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Math | 1415 | 1475 |
| OTIS Mock AIME 2024-2025 | 73.1% | — |
| Omni-MATH | 38.5% | — |
| FrontierMath (Feb 2025 set) | 4.8% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Hy3 leads
Gemini 2.5 Flash: 36.1 (#162), Hy3: 40.2 (#108)
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Expert | 1426 | 1461 |
| Humanity's Last Exam | 12.1% | — |
| MMLU-Pro | 63.9% | — |
| Confabulations | 16.8% | — |
| Vectara Hallucination Rate | 7.8% | — |
| GPQA (HELM) | 39% | — |
Multimodal Not comparable
Gemini 2.5 Flash: 41.2 (#31), Hy3: —
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Vision | 1254 | — |
| GeoBench | 76% | — |
| VPCT | 46.2% | — |
| SpatialViz-Bench | 36.9% | — |
Multilingual Hy3 leads
Gemini 2.5 Flash: 52.5 (#83), Hy3: 53.7 (#60)
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Non-English | 1410 | 1427 |
| LMArena Chinese | 1450 | 1496 |
| LMArena French | 1433 | 1461 |
| LMArena Korean | 1385 | 1390 |
| LMArena Russian | 1415 | 1435 |
| LMArena Spanish | 1421 | 1448 |
| LMArena German | 1419 | — |
| LMArena Japanese | 1403 | — |
Instruction Following Too close to call
Gemini 2.5 Flash: 75.9 (#50), Hy3: 75.3 (#68)
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1425 |
| IFEval | 89.8% | — |
Long Context Gemini 2.5 Flash leads
Gemini 2.5 Flash: 47.5 (#16), Hy3: 44.1 (#70)
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Longer Query | 1419 | 1443 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Hy3 leads
Gemini 2.5 Flash: 54.0 (#153), Hy3: 62.5 (#75)
| Benchmark | Gemini 2.5 Flash | Hy3 |
|---|---|---|
| LMArena Text | 1417 | 1442 |
| LMArena Creative Writing | 1400 | 1399 |
| LMArena Multi-Turn | 1408 | 1436 |
| Short-Story Creative Writing | 76.5% | — |
| EQ-Bench Creative Writing | 1137 | — |
| WildBench | 81.7% | — |
Frequently asked questions
Is Gemini 2.5 Flash better than Hy3?
Hy3 is the stronger model overall, scoring 43.6 to 39.0 on the Noometry Index.
Which is cheaper, Gemini 2.5 Flash or Hy3?
Hy3 is cheaper. It lists at $0.13 per million input tokens and $0.53 per million output tokens; Gemini 2.5 Flash lists at $0.30 and $2.50.
Is Gemini 2.5 Flash or Hy3 better for coding?
Hy3 scores higher on coding benchmarks: 46.6 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Gemini 2.5 Flash does, with 1.05M tokens against 262K.
How many benchmarks do Gemini 2.5 Flash and Hy3 share?
15 benchmarks have published results for both models. Gemini 2.5 Flash has 54 scored results on Noometry and Hy3 has 17.