There is very little daylight between Claude Haiku 5.5 (Max) (Anthropic) and Tencent Hy4 (Tencent) on the overall index. The figures come from tracked catalogue data, not from our own testing, so treat them as a starting point for a trial on your tasks. What separates them most is responsiveness; Claude Haiku 5.5 Max takes 4.6 minutes to produce its first token, Tencent Hy4 2.4 seconds.
Waiting time
Measured output speed is 233 tokens per second for Claude Haiku 5.5 Max and 94 tokens per second for Tencent Hy4. That makes Claude Haiku 5.5 Max roughly 2.5 times as fast at writing. The wait for the first token averages 4.6 minutes on Claude Haiku 5.5 Max against 2.4 seconds on Tencent Hy4. On total time, Tencent Hy4 wins at ordinary lengths; Claude Haiku 5.5 Max's higher throughput only pays off beyond about 43,000 tokens. A first-token wait of that length suits background work better than live conversation.
Add the two numbers up for a 2,000-token reply and Tencent Hy4 finishes first: 4.8 minutes for Claude Haiku 5.5 Max, 24 seconds for Tencent Hy4.
When they came out
The release dates are October 7, 2026 for Claude Haiku 5.5 Max and November 3, 2026 for Tencent Hy4, 27 days apart. That is close enough to count them as the same generation.
Token pricing and a sample bill
The list prices are $0.10 in and $0.50 out for Claude Haiku 5.5 Max, and $0.834 in and $2.501 out for Tencent Hy4, per million tokens. For output tokens, Tencent Hy4 is 5 times the price of Claude Haiku 5.5 Max.
For a sample workload of 1 million input tokens and 200,000 output tokens, Claude Haiku 5.5 Max would cost $0.20 and Tencent Hy4 $1.33, a difference of $1.13. For classifying 100,000 short messages at 150 input tokens and 5 output tokens each, Claude Haiku 5.5 Max would come in 87% lower: $1.75 for Claude Haiku 5.5 Max against $13.76 for Tencent Hy4. On a 3:1 blend of input to output tokens, that works out to $0.20 versus $1.251 per million.
Claude Haiku 5.5 Max leads on the intelligence index
Claude Haiku 5.5 Max comes out ahead on the intelligence index, 36.5 to 34.6. The lead is visible but narrow, so it should not decide the choice on its own. Put another way, Tencent Hy4 would need 5% more on this index to draw level.
For context, that places Claude Haiku 5.5 Max 37th and Tencent Hy4 42nd out of 109 scored models still on offer.
The catalogue does not yet split either model's score into coding and math indexes.
Score per dollar
Per point of intelligence index, Claude Haiku 5.5 Max costs $0.0055 of blended price per million tokens and Tencent Hy4 $0.036. Claude Haiku 5.5 Max scores higher and costs less per point, so on price per point there is nothing to trade off.

Comments (0)
to join the discussion
No comments yet
Be the first to share your thoughts!