Claude Haiku 5.5 Max vs GPT-5.6 Terra Max compared

Claude Haiku 5.5 Max leads the intelligence index 36.5 to 32.3. Benchmarks, sample bills, speed and a verdict.

Metric	Claude Haiku 5.5 (Max)	GPT-5.6 Terra (Max)
Intelligence Index	36.5	32.3
Input price (per 1M tokens)	$0.10	$2.00
Output price (per 1M tokens)	$0.50	$12.00
Output speed (tokens/s)	233	116
Time to first token	4.6 min	3.4 min
Release date	2026-10-07	2026-07-09

Metric

Claude Haiku 5.5 (Max)

GPT-5.6 Terra (Max)

Intelligence Index

36.5

32.3

Input price (per 1M tokens)

$0.10

$2.00

Output price (per 1M tokens)

$0.50

$12.00

Output speed (tokens/s)

233

116

Time to first token

4.6 min

3.4 min

Release date

2026-10-07

2026-07-09

Claude Haiku 5.5 (Max) from Anthropic and GPT-5.6 Terra (Max) from OpenAI 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 4% of GPT-5.6 Terra Max's blended rate. Everything below is read from the benchmark, price and speed data in Franklin AI's catalogue; nothing here comes from a hands-on test.

What they cost

Per million tokens, Claude Haiku 5.5 Max charges $0.10 for input and $0.50 for output, while GPT-5.6 Terra Max charges $2.00 and $12.00. That makes Claude Haiku 5.5 Max's output 96% cheaper.

For a sample workload of 1 million input tokens and 200,000 output tokens, Claude Haiku 5.5 Max would cost $0.20 and GPT-5.6 Terra Max $4.40, a difference of $4.20. Scale it up to classifying 100,000 short messages at 150 input tokens and 5 output tokens each and the bill is $1.75 for Claude Haiku 5.5 Max against $36.00 for GPT-5.6 Terra Max.

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 32.3. A lead of this size is hard to dismiss as noise.

For context, that places Claude Haiku 5.5 Max 37th and GPT-5.6 Terra Max 46th out of 109 scored models still on offer.

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

Cost per point of intelligence

Dividing the blended price by the intelligence index gives a rough cost per point: $0.0055 for Claude Haiku 5.5 Max and $0.14 for GPT-5.6 Terra Max, per million tokens. With the higher score and the lower cost per point, Claude Haiku 5.5 Max is the better value per point on these numbers.

Speed and latency

Measured output speed is 233 tokens per second for Claude Haiku 5.5 Max and 116 tokens per second for GPT-5.6 Terra Max. That makes Claude Haiku 5.5 Max roughly twice as fast at writing. Time to first token is 4.6 minutes for Claude Haiku 5.5 Max and 3.4 minutes for GPT-5.6 Terra Max. On total time, GPT-5.6 Terra Max wins at ordinary lengths; Claude Haiku 5.5 Max's higher throughput only pays off beyond about 17,000 tokens. A first-token wait of that length suits background work better than live conversation.

Put together, a 2,000-token answer would take about 4.8 minutes from Claude Haiku 5.5 Max and 3.7 minutes from GPT-5.6 Terra Max, counting the first-token wait.

Which is newer

Claude Haiku 5.5 Max arrived on October 7, 2026, about 3 months after GPT-5.6 Terra Max (July 9, 2026).

FAQ

Is Claude Haiku 5.5 Max better than GPT-5.6 Terra Max?

Neither wins everywhere: Claude Haiku 5.5 Max scores higher on the intelligence index, 36.5 to 32.3; Claude Haiku 5.5 Max is 96% cheaper on blended price; Claude Haiku 5.5 Max streams output twice as fast; and GPT-5.6 Terra Max reaches its first token sooner.

Are Claude Haiku 5.5 Max and GPT-5.6 Terra Max from the same company?

Claude Haiku 5.5 Max is made by Anthropic and GPT-5.6 Terra Max by OpenAI. Claude Haiku 5.5 Max was released on October 7, 2026 and GPT-5.6 Terra Max on July 9, 2026.

Which is cheaper, Claude Haiku 5.5 Max or GPT-5.6 Terra 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; GPT-5.6 Terra Max lists $2.00 and $12.00. For 1 million input and 200,000 output tokens that is $0.20 against $4.40.

Which model has lower latency?

Claude Haiku 5.5 Max generates output faster, at 233 tokens per second against 116 tokens per second. GPT-5.6 Terra Max reaches its first token sooner (3.4 minutes against 4.6 minutes). Counting the first-token wait, GPT-5.6 Terra Max finishes first for any reply shorter than about 17,000 tokens.

When were Claude Haiku 5.5 Max and GPT-5.6 Terra Max released?

Claude Haiku 5.5 Max is newer. It was released on October 7, 2026, about 3 months after GPT-5.6 Terra Max (July 9, 2026).

Final whistle

Bottom line: Claude Haiku 5.5 Max has more going for it here, but GPT-5.6 Terra Max is not without an argument. Pick Claude Haiku 5.5 Max if cost matters ($0.50 against $12.00 per million output tokens) and you need the higher overall score (36.5 against 32.3). Pick GPT-5.6 Terra Max if replies need to finish sooner at typical lengths 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 Claude Haiku 5.5 (Max) and GPT-5.6 Terra (Max) pages. The AI Benchmark methodology explains how that data is collected and shown.