# Gemini 3.8 Flash vs Hy3

> Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 44.2 on the Noometry Index. Hy3 costs 10× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gemini-3-8-flash-vs-hy3
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Gemini 3.8 Flash scores higher in 8 categories and Hy3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Gemini 3.8 Flash leads 76.9 to 26.1.
- The biggest single-benchmark swing is NYT Connections (extended): 97.4% for Gemini 3.8 Flash and 41.2% for Hy3.
- Hy3 is cheaper at $0.0825 / $0.33 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.8 Flash.
- Gemini 3.8 Flash accepts more context: 1.05M tokens versus 262K.
- Hy3 has downloadable open weights; the other is API-only.

## Snapshot

| | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| Provider | Google | Tencent |
| Noometry Index | 61.8 | 44.2 |
| Rank | 11 | 79 |
| Context | 1.05M | 262K |
| Input $/M | $0.75 | $0.0825 |
| Output $/M | $3.75 | $0.33 |
| Weights | Proprietary | Open |

## Coding

- Gemini 3.8 Flash: 59.2 (#15)
- Hy3: 46.8 (#63)

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| LMArena WebDev | 1584 | 1508 |
| LMArena Coding | 1510 | 1464 |
| DeepSWE | 73.8% | — |
| FrontierCode | 41.2% | — |
| CursorBench | 39.6% | — |
| FrontierSWE | 19.6% | — |
| SciCode | 56.6% | — |
| WeirdML | 84.8% | — |
| ALE-Bench | 1,270 | — |

## Agentic & Tool Use

- Gemini 3.8 Flash: 41.8 (#21)
- Hy3: —

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| APEX-Agents | 64.3% | — |
| Remote Labor Index | 5.8% | — |
| GDP.pdf | 23.4% | — |
| Vending-Bench 2 | 5,094 | — |

## Reasoning

- Gemini 3.8 Flash: 76.9 (#5)
- Hy3: 26.1 (#136)

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| NYT Connections (extended) | 97.4% | 41.2% |
| LMArena Hard Prompts | 1508 | 1447 |
| ARC-AGI-2 | 89.2% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 18.3% | — |
| Chess Puzzles | 61% | — |
| Mystery Game Puzzles | 47% | — |
| DTBench | 95.7% | — |
| LMCA | 52.9% | — |
| Surface Evolver Bench | 76.9% | — |
| Epoch Capabilities Index | 156.71 | — |

## Math

- Gemini 3.8 Flash: 65.3 (#28)
- Hy3: 40.1 (#93)

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| LMArena Math | 1528 | 1475 |
| FrontierMath (Tiers 1-3) | 68.4% | — |
| FrontierMath Tier 4 | 22% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |
| ProofBench | 48% | — |

## Knowledge

- Gemini 3.8 Flash: 74.8 (#2)
- Hy3: 40.8 (#114)

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| LMArena Expert | 1524 | 1460 |
| GPQA Diamond | 95.4% | — |
| Humanity's Last Exam | 44.5% | — |
| SimpleQA Verified | 69.7% | — |

## Multimodal

- Gemini 3.8 Flash: 40.7 (#45)
- Hy3: —

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| LMArena Vision | 1314 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 31.7% | — |

## Multilingual

- Gemini 3.8 Flash: 58.0 (#5)
- Hy3: 53.5 (#65)

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| LMArena Non-English | 1491 | 1426 |
| LMArena Chinese | 1554 | 1493 |
| LMArena French | 1498 | 1461 |
| LMArena German | 1493 | 1439 |
| LMArena Japanese | 1502 | 1392 |
| LMArena Korean | 1459 | 1395 |
| LMArena Russian | 1515 | 1432 |
| LMArena Spanish | 1485 | 1456 |

## Instruction Following

- Gemini 3.8 Flash: 78.0 (#13)
- Hy3: 75.1 (#70)

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| LMArena Instruction Following | 1490 | 1426 |

## Long Context

- Gemini 3.8 Flash: 46.3 (#24)
- Hy3: 44.1 (#75)

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| LMArena Longer Query | 1508 | 1442 |

## Writing & Preference

- Gemini 3.8 Flash: 72.2 (#15)
- Hy3: 62.2 (#81)

| Benchmark | Gemini 3.8 Flash | Hy3 |
|---|---|---|
| LMArena Text | 1499 | 1439 |
| LMArena Creative Writing | 1492 | 1402 |
| LMArena Multi-Turn | 1501 | 1436 |
| EQ-Bench Creative Writing | 1748 | — |

## FAQ

### Is Gemini 3.8 Flash better than Hy3?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 44.2 on the Noometry Index. Hy3 costs 10× less per token, which makes it the better buy when Gemini 3.8 Flash's lead doesn't matter for your workload.

### Which is cheaper, Gemini 3.8 Flash or Hy3?

Hy3 is cheaper. It lists at $0.0825 per million input tokens and $0.33 per million output tokens; Gemini 3.8 Flash lists at $0.75 and $3.75.

### Is Gemini 3.8 Flash or Hy3 better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 46.8 in the Noometry coding category.

### Which has the bigger context window?

Gemini 3.8 Flash does, with 1.05M tokens against 262K.

### How many benchmarks do Gemini 3.8 Flash and Hy3 share?

19 benchmarks have published results for both models. Gemini 3.8 Flash has 50 scored results on Noometry and Hy3 has 19.