Head-to-head AI model comparison graphic: Gemini 4 Argon (Google) vs Tencent Hy4 (Tencent). Intelligence index 50.4 vs 34.6; output speed 89 vs 94 tokens per second; time to first token 51s vs 2.4s; output price $20.00 vs $2.501 per million tokens; input price $4.00 vs $0.834 per million tokens. franklineh.com
Gemini 4 Argon vs Tencent Hy4: head-to-head AI benchmark comparison. Tencent Hy4 leads on output speed, time to first token, output price and input price; Gemini 4 Argon leads on intelligence index.
Head to headBy Franklin AIUpdated

Gemini 4 Argon vs Tencent Hy4: benchmarks, price and speed

Gemini 4 Argon leads the intelligence index 50.4 to 34.6. Tencent Hy4 costs 84% less on blended price. Price per token, response speed and when to pick each.

Pick it for Gemini 4 Argon · High

  • Higher intelligence index: 50.4 against 34.6.

Pick it for Tencent Hy4

  • Lower cost: $1.33 against $8.00 for 1 million input and 200,000 output tokens.
  • Shorter wait for the first token: 2.4 seconds against 51 seconds.
  • The newer release (November 2026).

By the numbers

MetricGemini 4 Argon (High)Tencent Hy4
Intelligence Index50.434.6
Input price (per 1M tokens)$4.00$0.834
Output price (per 1M tokens)$20.00$2.501
Output speed (tokens/s)8994
Time to first token51s2.4s
Release date2026-09-302026-11-03

On paper this is a mismatch: Gemini 4 Argon (High) and Tencent Hy4 are separated by 15.8 points on the intelligence index. Their widest difference is the intelligence index, with Gemini 4 Argon ahead by 15.8 points (50.4 versus 34.6). Everything below is read from the benchmark, price and speed data in Franklin AI's catalogue; nothing here comes from a hands-on test.

Overall capability: 15.8 points apart

On the intelligence index, Gemini 4 Argon scores 50.4 against 34.6 for Tencent Hy4. These scores put the two models in different leagues on overall capability.

For context, that places Gemini 4 Argon 15th and Tencent Hy4 42nd out of 109 scored models still on offer.

There are no coding or math index scores for either model in the catalogue, which keeps this comparison at the aggregate level.

Which is newer

The release dates are September 30, 2026 for Gemini 4 Argon and November 3, 2026 for Tencent Hy4, 34 days apart. That is close enough to count them as the same generation.

What they cost

The list prices are $4.00 in and $20.00 out for Gemini 4 Argon, and $0.834 in and $2.501 out for Tencent Hy4, per million tokens. Gemini 4 Argon costs 8 times as much per output token.

A reference job of 1 million input tokens and 200,000 output tokens costs $8.00 with Gemini 4 Argon and $1.33 with Tencent Hy4, so Tencent Hy4 saves $6.67. Scale it up to an agent that reads 50 million tokens and writes 5 million in a month and the bill is $300 for Gemini 4 Argon against $54.20 for Tencent Hy4. Blended at three input tokens per output token, the effective rates are $8.00 for Gemini 4 Argon and $1.251 for Tencent Hy4.

Value for money

Dividing the blended price by the intelligence index gives a rough cost per point: $0.16 for Gemini 4 Argon and $0.036 for Tencent Hy4, per million tokens. Gemini 4 Argon costs 4.4 times as much per point, which is the price of its lead.

How fast they respond

Gemini 4 Argon generates about 89 tokens per second and Tencent Hy4 about 94 tokens per second. Throughput is close to level. The wait for the first token averages 51 seconds on Gemini 4 Argon against 2.4 seconds on Tencent Hy4. In an interactive app, Tencent Hy4 will feel noticeably more responsive. Waits that long are felt on every chat-style request, though they matter less for batch jobs.

Add the two numbers up for a 2,000-token reply and Tencent Hy4 finishes first: 73 seconds for Gemini 4 Argon, 24 seconds for Tencent Hy4.

FAQ

Is Tencent Hy4 better than Gemini 4 Argon?

It depends on what you need: Gemini 4 Argon scores higher on the intelligence index, 50.4 to 34.6; Tencent Hy4 is 84% cheaper on blended price; and Tencent Hy4 reaches its first token sooner.

Who makes Gemini 4 Argon and Tencent Hy4?

Gemini 4 Argon is made by Google and Tencent Hy4 by Tencent. Gemini 4 Argon was released on September 30, 2026 and Tencent Hy4 on November 3, 2026.

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.

Which is newer, Gemini 4 Argon or Tencent Hy4?

Tencent Hy4 is newer. It was released on November 3, 2026, 34 days after Gemini 4 Argon (September 30, 2026).

Which model has lower latency?

Their output speeds are close: 89 tokens per second for Gemini 4 Argon and 94 tokens per second for Tencent Hy4. Tencent Hy4 reaches its first token sooner (2.4 seconds against 51 seconds).

Final whistle

Short answer: it is close, with Gemini 4 Argon and Tencent Hy4 each holding a real advantage. Pick Tencent Hy4 if cost matters ($2.501 against $20.00 per million output tokens) and users are waiting on the first word. Pick Gemini 4 Argon if you need the higher overall score (50.4 against 34.6).

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 Gemini 4 Argon (High) and Tencent Hy4 pages. The AI Benchmark methodology explains how that data is collected and shown.

Comments (0)

No comments yet

Be the first to share your thoughts!