GPT-6 Astra Max vs Tencent Hy4: benchmark scores compared

GPT-6 Astra Max leads the intelligence index 56.9 to 34.6. Tencent Hy4 costs 94% less on blended price. Price per token, response speed and when to pick each.

Metric	GPT-6 Astra (Max)	Tencent Hy4
Intelligence Index	56.9	34.6
Input price (per 1M tokens)	$10.00	$0.834
Output price (per 1M tokens)	$50.00	$2.501
Output speed (tokens/s)	46	94
Time to first token	6.8 min	2.4s
Release date	2026-09-03	2026-11-03

Metric

GPT-6 Astra (Max)

Tencent Hy4

Intelligence Index

56.9

34.6

Input price (per 1M tokens)

$10.00

$0.834

Output price (per 1M tokens)

$50.00

$2.501

Output speed (tokens/s)

Time to first token

6.8 min

2.4s

Release date

2026-09-03

2026-11-03

GPT-6 Astra (Max) (OpenAI) and Tencent Hy4 (Tencent) are not peers on the headline index, which makes the trade-offs the interesting part. What follows is built entirely from tracked data, so where the catalogue is silent, this page says so instead of guessing. GPT-6 Astra Max leads the intelligence index 56.9 to 34.6, a gap of 22.3 points.

Overall capability: 22.3 points apart

On the intelligence index, GPT-6 Astra Max scores 56.9 against 34.6 for Tencent Hy4. A gap this large suggests the two are built for different jobs. In relative terms, GPT-6 Astra Max scores 64% higher.

Among 109 active scored models, GPT-6 Astra Max sits 5th and Tencent Hy4 42nd.

Specialist coding and math indexes are missing for both, so treat the overall score as the only capability signal here.

Throughput and time to first token

GPT-6 Astra Max generates about 46 tokens per second and Tencent Hy4 about 94 tokens per second. Tencent Hy4 is ahead by 103% on throughput. Time to first token is 6.8 minutes for GPT-6 Astra Max and 2.4 seconds for Tencent Hy4. GPT-6 Astra Max waits 173 times as long before its first token. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

Put together, a 2,000-token answer would take about 7.5 minutes from GPT-6 Astra Max and 24 seconds from Tencent Hy4, counting the first-token wait.

Running costs

The list prices are $10.00 in and $50.00 out for GPT-6 Astra Max, and $0.834 in and $2.501 out for Tencent Hy4, per million tokens. That makes Tencent Hy4's output 95% cheaper.

A reference job of 1 million input tokens and 200,000 output tokens costs $20.00 with GPT-6 Astra Max and $1.33 with Tencent Hy4, so Tencent Hy4 saves $18.67. Scale it up to a month of coding-assistant traffic at 30 million input and 3 million output tokens and the bill is $450 for GPT-6 Astra Max against $32.52 for Tencent Hy4. On a 3:1 blend of input to output tokens, that works out to $20.00 versus $1.251 per million.

When they came out

Tencent Hy4 arrived on November 3, 2026, about 2 months after GPT-6 Astra Max (September 3, 2026).

Score per dollar

Dividing the blended price by the intelligence index gives a rough cost per point: $0.35 for GPT-6 Astra Max and $0.036 for Tencent Hy4, per million tokens. Tencent Hy4 delivers each index point for 90% less; whether GPT-6 Astra Max's extra 22.3 points are worth the premium depends on how often your tasks need them.

Frequently asked questions

Is Tencent Hy4 better than GPT-6 Astra Max?

Neither wins everywhere: GPT-6 Astra Max scores higher on the intelligence index, 56.9 to 34.6; Tencent Hy4 is 94% cheaper on blended price; and Tencent Hy4 streams output twice as fast.

Where do these numbers come from?

The figures are the recorded benchmark, price and speed data in Franklin AI's model catalogue. This page is written from that data automatically; neither model was tested by hand for it.

How much do GPT-6 Astra Max and Tencent Hy4 cost?

Tencent Hy4 is cheaper on a blended basis. GPT-6 Astra Max lists $10.00 per million input tokens and $50.00 per million output tokens; Tencent Hy4 lists $0.834 and $2.501. For 1 million input and 200,000 output tokens that is $20.00 against $1.33.

Which is faster, GPT-6 Astra Max or Tencent Hy4?

Tencent Hy4 generates output faster, at 94 tokens per second against 46 tokens per second. Tencent Hy4 reaches its first token sooner (2.4 seconds against 6.8 minutes).

Are GPT-6 Astra Max and Tencent Hy4 from the same company?

GPT-6 Astra Max is made by OpenAI and Tencent Hy4 by Tencent. GPT-6 Astra Max was released on September 3, 2026 and Tencent Hy4 on November 3, 2026.

Final whistle

Bottom line: on balance the numbers favour Tencent Hy4, though GPT-6 Astra Max keeps a case of its own. Pick GPT-6 Astra Max if you need the higher overall score (56.9 against 34.6). Pick Tencent Hy4 if cost matters ($2.501 against $50.00 per million output tokens) and users are waiting on the first word.

Where the numbers come from

The scores, speed and prices in this comparison come from independent third-party model evaluations that Franklin AI syncs each day, and the article was written from a snapshot of them. For the latest results, open the GPT-6 Astra (Max) and Tencent Hy4 pages. The AI Benchmark methodology explains how that data is collected and shown.