Hy3
By Tencent · released 2026-07-06 (3 months) · snapshot 2026-10-24
- Intelligence index
- 25.30
- Cost to run the AA index
- $150
- Price per 1M tokens (in / out)
- $0.14 / $0.56
- End-to-end time
- 33.3s
Is Hy3 on the Pareto frontier, and what beats it?
Off the frontier
No. GPT-6 Luna (Max) is at least as smart for the same money or less.
Next step up: Claude Haiku 5.5 (Xhigh), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | Hy3 | Tencent | 25.30 | $150 | 33.3s | 2026-07-06 | ||
| 2 | GPT-6 Luna (Max) | OpenAI | 38.10 | $122 | 82.0s | 2026-09-22 | Frontier | |
| 3 | Claude Haiku 5.5 (Xhigh) | Anthropic | 41.20 | $158 | 59.8s | 2026-10-07 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
Hy3 today
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: hy3.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
What the Hy3 release did to the frontier on 2026-07-06
1 of 1 effort levels reached the frontier at launch (Hy3). Impact 0.17, #36 of 46 releases this past year.
Should you use Hy3?
Should you use Hy3?
Only when it fits your setup: GPT-6 Luna (Max) is at least as smart for the same money or less, so Hy3 is off the value frontier today.
What is better and cheaper than Hy3?
GPT-6 Luna (Max) — at least as smart for the same money or less.
How much does Hy3 cost?
$0.14/$0.56 in/out per 1M tokens, and $150 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is Hy3 on the Pareto frontier?
No: GPT-6 Luna (Max) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where Hy3 is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/hy3 · Markdown: /api/v1/models/hy3?format=md · llms.txt · agent skill