Hy4 previewvsHy3
Across 7 shared benchmarks, Hy4 preview leads overall: Hy4 preview wins 7, Hy3 wins 0, with 0 ties and an average score difference of +10.51.
Hy4 preview
腾讯AI实验室 · 2026-08-28 · Reasoning model
Hy3
腾讯AI实验室 · 2026-07-06 · Reasoning model
Hy4 preview7 wins(100%)(0%)0 winsHy3
Benchmark scores
Grouped by capability, sorted by largest gap within each. 7 shared benchmarks.
Coding and Software Engineer
Hy4 preview 3/3| Benchmark | Hy4 preview | Hy3 | Diff |
|---|---|---|---|
| DeepSWE | 64.3011 / 31Thinking High (With Tools) | 2830 / 31Thinking High (With Tools) | +36.30 |
| SWE-Bench Pro - Public | 65.706 / 59Thinking High (With Tools) | 57.9020 / 59Thinking High (With Tools) | +7.80 |
| SWE-bench Multilingual | 82.903 / 27Thinking High (With Tools) | 75.8010 / 27Thinking High (With Tools) | +7.10 |
AI Agent - Tool Usage
Hy4 preview 2/2| Benchmark | Hy4 preview | Hy3 | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 85.4010 / 47Thinking High (With Tools) | 71.7033 / 47Thinking High (With Tools) | +13.70 |
| MCP-Atlas | 83.705 / 40Thinking High (With Tools) | 79.1011 / 40Thinking High (With Tools) | +4.60 |
General Evaluation
Hy4 preview 1/1| Benchmark | Hy4 preview | Hy3 | Diff |
|---|---|---|---|
| GPQA Diamond | 92.3024 / 226Thinking High (No Tools) | 90.4038 / 226Thinking High (No Tools) | +1.90 |
General Knowledge
Hy4 preview 1/1| Benchmark | Hy4 preview | Hy3 | Diff |
|---|---|---|---|
| HLE | 55.4015 / 185Thinking High (With Tools) | 53.2021 / 185Thinking High (With Tools) | +2.20 |
Specs
| Field | Hy4 preview | Hy3 |
|---|---|---|
| Publisher | 腾讯AI实验室 | 腾讯AI实验室 |
| Release date | 2026-08-28 | 2026-07-06 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 770B | 295B |
| Context length | 1M | 256K |
| Max output | Not available | Not available |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Hy4 preview | Hy3 |
|---|---|---|
| Text input | ¥6 / 1M tokens | ¥1.2 / 1M tokens |
| Text output | ¥18 / 1M tokens | ¥4 / 1M tokens |
| Cache read | ¥0.3 / 1M tokens | ¥0.4 / 1M tokens |
Summary
- Hy4 previewleads in:Coding and Software Engineer (3/3), AI Agent - Tool Usage (2/2), General Evaluation (1/1), General Knowledge (1/1)
On average across the 7 shared benchmarks, Hy4 preview scores 10.51 higher.
Largest single-benchmark gap: DeepSWE — Hy4 preview 64.30 vs Hy3 28 (+36.30).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.