Claude Haiku 5.5 Max vs GLM-5.3 Max compared

Claude Haiku 5.5 Max leads the intelligence index 36.5 to 31.7. Price per token, response speed and when to pick each.

Metric	Claude Haiku 5.5 (Max)	GLM-5.3 (Max)
Intelligence Index	36.5	31.7
Input price (per 1M tokens)	$0.10	$1.40
Output price (per 1M tokens)	$0.50	$4.40
Output speed (tokens/s)	233	74
Time to first token	4.6 min	1.7s
Release date	2026-10-07	2026-08-18

Metric

Claude Haiku 5.5 (Max)

GLM-5.3 (Max)

Intelligence Index

36.5

31.7

Input price (per 1M tokens)

$0.10

$1.40

Output price (per 1M tokens)

$0.50

$4.40

Output speed (tokens/s)

233

Time to first token

4.6 min

1.7s

Release date

2026-10-07

2026-08-18

Claude Haiku 5.5 (Max) from Anthropic and GLM-5.3 (Max) from Z AI are both tracked in Franklin AI's benchmark catalogue. Cost is where they split the most, with Claude Haiku 5.5 Max working out at about 9% of GLM-5.3 Max's blended rate. This page is written automatically from catalogue numbers only: benchmark scores, list prices and measured speed.

What they cost

Claude Haiku 5.5 Max lists $0.10 per million input tokens and $0.50 per million output tokens; GLM-5.3 Max lists $1.40 and $4.40. GLM-5.3 Max costs 8.8 times as much per output token.

Take 1 million input tokens and 200,000 output tokens: that comes to $0.20 on Claude Haiku 5.5 Max and $2.28 on GLM-5.3 Max. Scale it up to extracting fields from 20,000 pages of 1,500 tokens into 150-token records and the bill is $4.50 for Claude Haiku 5.5 Max against $55.20 for GLM-5.3 Max.

Which is newer

GLM-5.3 Max came first, on August 18, 2026; Claude Haiku 5.5 Max followed on October 7, 2026.

How fast they respond

Once a response is under way, Claude Haiku 5.5 Max produces roughly 233 tokens per second against 74 tokens per second for GLM-5.3 Max. That makes Claude Haiku 5.5 Max roughly 3.2 times as fast at writing. Before any text appears, Claude Haiku 5.5 Max takes 4.6 minutes and GLM-5.3 Max 1.7 seconds. The faster writer, Claude Haiku 5.5 Max, gives away too much at the start to win on time: counting the first-token wait, GLM-5.3 Max finishes first for any reply shorter than about 30,000 tokens. A first-token wait of that length suits background work better than live conversation.

Put together, an 800-token answer would take about 4.7 minutes from Claude Haiku 5.5 Max and 13 seconds from GLM-5.3 Max, counting the first-token wait.

The headline benchmark

Claude Haiku 5.5 Max comes out ahead on the intelligence index, 36.5 to 31.7. That is a clear margin for an index that averages many evaluations. In relative terms, Claude Haiku 5.5 Max scores 15% higher.

For context, that places Claude Haiku 5.5 Max 37th and GLM-5.3 Max 47th 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.

Score per dollar

Per point of intelligence index, Claude Haiku 5.5 Max costs $0.0055 of blended price per million tokens and GLM-5.3 Max $0.068. With the higher score and the lower cost per point, Claude Haiku 5.5 Max is the better value per point on these numbers.

Common questions about Claude Haiku 5.5 Max and GLM-5.3 Max

Is GLM-5.3 Max better than Claude Haiku 5.5 Max?

Not across the board: Claude Haiku 5.5 Max scores higher on the intelligence index, 36.5 to 31.7; Claude Haiku 5.5 Max is 91% cheaper on blended price; Claude Haiku 5.5 Max streams output 3.2 times as fast; and GLM-5.3 Max reaches its first token sooner.

Which is cheaper, Claude Haiku 5.5 Max or GLM-5.3 Max?

Claude Haiku 5.5 Max is cheaper on a blended basis. Claude Haiku 5.5 Max lists $0.10 per million input tokens and $0.50 per million output tokens; GLM-5.3 Max lists $1.40 and $4.40. For 1 million input and 200,000 output tokens that is $0.20 against $2.28.

When were Claude Haiku 5.5 Max and GLM-5.3 Max released?

Claude Haiku 5.5 Max is newer. It was released on October 7, 2026, about 2 months after GLM-5.3 Max (August 18, 2026).

Does Claude Haiku 5.5 Max respond faster than GLM-5.3 Max?

Claude Haiku 5.5 Max generates output faster, at 233 tokens per second against 74 tokens per second. GLM-5.3 Max reaches its first token sooner (1.7 seconds against 4.6 minutes). Counting the first-token wait, GLM-5.3 Max finishes first for any reply shorter than about 30,000 tokens.

Was this comparison tested by hand?

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.

Final whistle

In one line: Claude Haiku 5.5 Max is the stronger all-round pick on this data, while GLM-5.3 Max makes sense in narrower cases. Pick Claude Haiku 5.5 Max if cost matters ($0.50 against $4.40 per million output tokens) and you need the higher overall score (36.5 against 31.7). Pick GLM-5.3 Max if users are waiting on the first word and replies need to finish sooner at typical lengths.

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 Claude Haiku 5.5 (Max) and GLM-5.3 (Max) pages. The AI Benchmark methodology explains how that data is collected and shown.