Gemini 4 Carbon High vs Tencent Hy4: benchmark scores compared

On paper this is a mismatch: Gemini 4 Carbon (High) and Tencent Hy4 are separated by 25.4 points on the intelligence index. Everything below is read from the benchmark, price and speed data in Franklin AI's catalogue; nothing here comes from a hands-on test. Gemini 4 Carbon High leads the intelligence index 60.0 to 34.6, a gap of 25.4 points.

How the intelligence index compares

Gemini 4 Carbon High records 60.0 on the intelligence index and Tencent Hy4 records 34.6. A gap this large suggests the two are built for different jobs. In relative terms, Gemini 4 Carbon High scores 73% higher.

Among 109 active scored models, Gemini 4 Carbon High sits 1st and Tencent Hy4 42nd.

The catalogue does not yet split either model's score into coding and math indexes.

Running costs

Per million tokens, Gemini 4 Carbon High charges $4.00 for input and $20.00 for output, while Tencent Hy4 charges $0.834 and $2.501. That makes Tencent Hy4's output 87% cheaper.

A reference job of 1 million input tokens and 200,000 output tokens costs $8.00 with Gemini 4 Carbon High and $1.33 with Tencent Hy4, so Tencent Hy4 saves $6.67. A bigger example, summarising 1,000 documents of 8,000 tokens into 400-token summaries, costs $40.00 on Gemini 4 Carbon High and $7.67 on Tencent Hy4: a gap of $32.33.

Value for money

A blunt value measure, blended price over intelligence score, puts Gemini 4 Carbon High at $0.13 and Tencent Hy4 at $0.036 per point. So Gemini 4 Carbon High buys its higher score at a premium, while Tencent Hy4 is the value pick, paying 73% less per point.

Generation gap

The release dates are October 28, 2026 for Gemini 4 Carbon High and November 3, 2026 for Tencent Hy4, 6 days apart. They are effectively contemporaries.

Throughput and time to first token

Once a response is under way, Gemini 4 Carbon High produces roughly 91 tokens per second against 94 tokens per second for Tencent Hy4. There is little to choose between them on raw output speed. The wait for the first token averages 2.0 minutes on Gemini 4 Carbon High against 2.4 seconds on Tencent Hy4. Tencent Hy4 gets to its first token 51 times as fast. A first-token wait of that length suits background work better than live conversation.

Put together, a 1,000-token answer would take about 2.2 minutes from Gemini 4 Carbon High and 13 seconds from Tencent Hy4, counting the first-token wait.