# Hy3 Benchmark Scores & Performance

> Hy3 by Tencent scores 52.62/100 overall, ranking #78 out of 783 AI models.

Canonical page: https://benchlm.ai/models/hy3

Last updated: October 5, 2026

## Model Details

| Property | Value |
|----------|-------|
| Creator | Tencent |
| Source Type | Open Weight |
| Reasoning Type | Reasoning |
| Context Window | 256K |
| Overall Score | 52.62/100 |
| Overall Rank | #78 of 783 |

## Family & Coverage

- Family: Hy3
- Variant: instruct
- Benchmarks covered: 14 of 646
- Sibling models: [Hy3 Preview](/models/hy3-preview)
- Related earlier model: [Hy3 Preview](/models/hy3-preview)
- Coverage note: BenchLM currently has partial benchmark coverage for this model, so the overall score is conservative.

## Agentic Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [GDPval-AA](/benchmarks/gdpvalaanormalized) | 27.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [AA Agentic Index](/benchmarks/aaagenticindex) | 25.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [GDPval-AA](/benchmarks/gdpvalaa) | 1136 | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |

## Coding Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-SciCode](/benchmarks/aascicode) | 48.6% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [AA Coding Index](/benchmarks/aacodingindex) | 58.8% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |

## Multimodal & Grounded Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Design Arena Website](/benchmarks/designarenawebsite) | 1189 | [OpenRouter model benchmarks](https://openrouter.ai/tencent/hy3/benchmarks) |

## Reasoning Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [AA-LCR](/benchmarks/lcr) | 79.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [CritPt](/benchmarks/critpt) | 4.9% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |

## Knowledge Benchmarks

| Benchmark | Score | Source |
|-----------|-------|--------|
| [Artificial Analysis Intelligence Index](/benchmarks/artificialanalysis) | 25.3% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [AA-GPQA Diamond](/benchmarks/aagpqadiamond) | 89.7% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [AA-HLE](/benchmarks/aahle) | 33.5% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [AA-Omniscience Index](/benchmarks/aaomniscienceindex) | -18.5% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [AA-Omniscience Accuracy](/benchmarks/omniscienceaccuracy) | 32.0% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |
| [AA-Omniscience Hallucination Rate](/benchmarks/omnisciencehallucinationrate) | 74.1% | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/hy3) |

## Other Tencent Models

- [Hy4 preview](/models/hy4-preview) - Score: 60.91
- [Hy3 Preview](/models/hy3-preview) - Score: 50.98
- [UI-Mate-27B](/models/ui-mate-27b) - Score: not computed
- [UI-Mate-9B](/models/ui-mate-9b) - Score: not computed
- [AuK](/models/tencent-auk) - Score: not computed
- [Hy ASR 3.0 preview](/models/hy-asr-3-0-preview) - Score: not computed
- [Hy-MT2-1.8B](/models/hy-mt2-1-8b) - Score: not computed
- [Hy-MT2-30B-A3B](/models/hy-mt2-30b-a3b) - Score: not computed