cd /news/artificial-intelligence/gpt-live-1-1-is-faster-and-follows-s… · home › topics › artificial-intelligence › article
[ARTICLE · art-173082] src=thunderphone.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

GPT-Live-1.1 is faster and follows scripts better, but still slips on spellings and read-backs

OpenAI's GPT-Live-1.1, now available in the API, responds faster on phone lines, repeats caller speech more accurately and matches approved business replies more often than GPT-Live-1, but still fails on spelled names, chunked phone numbers and re-asking scripted questions, according to a same-day comparison test. In 50 simulated calls to invented businesses, 40 had no misheard details or broken instructions while the rest had at least one caller-noticeable mistake; a caller's "oh three hundred" callback ending was heard as 3000, "Brianna" was repeated as "Rhiata," and C-O-R-B-E-L was read back with an extra L. The model handled rule reasoning cleanly, telling an auto-shop caller "November 26th is Thanksgiving, so I can't confirm an appointment that day" and holding firm that a $129 diagnostic fee "is not waived or credited.

recommendation

Replay real call transcripts turn by turn and score replies against approved scripts, including spelled names and chunked numbers, to catch regressions like "Brianna" read back as "Rhiata."

more in playbook: Evals and testing for LLM apps
by read4 min views2 publishedNov 19, 2026
GPT-Live-1.1 is faster and follows scripts better, but still slips on spellings and read-backs
Image: Thunderphone (auto-discovered)

← All posts OpenAI's GPT-Live-1.1 responds faster on a phone line than GPT-Live-1, repeats caller speech more accurately, and matches approved business replies more often. It still struggles when callers spell out names, mangles chunked phone numbers during read-backs, and re-asks scripted questions the caller has already answered.

When the first version arrived in September, we found natural pacing paired with unreliable script adherence and character-level mistakes. With 1.1 now in the API, we reran our tests alongside the first version on the same day as a control. One test asks the model to repeat caller clips from phone calls word for word; the other replays real business phone calls turn by turn and checks the model's reply against the reply the business approved.

We left out transfers, hang-ups, and tool timing because they depend on our setup as much as on the model.

The new model is noticeably brisker to speak and noticeably more likely to give the reply a business wanted, with a smaller gain on verbatim hearing.

To hear how 1.1 behaves across full conversations, we ran 50 simulated calls to invented businesses, from a pizza shop to a city 311 line. Every business, caller, and phone number in these examples is invented. A scripted AI caller laid traps such as spelled names and chunked phone numbers. Each scenario ran once, so what follows are examples rather than rates.

Forty of the 50 calls had no misheard details or broken instructions. The rest had at least one mistake a caller would notice.

Names, numbers, and spellings #

Callers rarely read digits at an even pace; they group them into hundreds or mix "oh" with digits. At the pest-control company, a caller ended a callback number with "oh three hundred," and the agent heard 3000:

At the vet clinic, a caller gave a phone number using "oh" for zero. Reading it back, the agent regrouped the chunks and added an extra five:

Spoken and spelled names were just as fragile. A pizza caller named "Brianna" got repeated back as "Rhiata." In a vet call that switched to Spanish, a caller spelled Echeverría as "E-C-H-E-V de vaca-E-doble erre-I-A," and the agent confirmed the V with "B as in Bravo," dropping English phonetics into Spanish.

On the other hand, 1.1 handled several deliberate traps cleanly. We planted dummy names and numbers in prompts to see if the model would parrot its instructions instead of listening. The vet prompt's example spelled "Delacroix," yet when a caller named Delacorte phoned in, the agent spelled D-E-L-A-C-O-R-T-E right. It passed a similar trap at the gym, where the prompt's read-back example used 312-555-0142; when our caller gave 312-555-0164 in halting chunks, the agent read back the caller's real digits instead of the example:

Scripts, checklists, and rules #

In September, the first version treated checklists mechanically, asking scripted questions the caller had just answered. The new model still falls into that rut.

The pizza shop's instructions say to ask quantity, size, and toppings "only for details not already given." Our caller gave all three in four words, and the agent asked every one anyway:

The same thing happened at the pest-control company after a caller gave a full street, unit status, city, and zip code in one breath. Right after the caller spelled C-O-R-B-E-L, the agent read it back with an extra L, then asked for the unit, city, and zip one by one:

Where 1.1 looked sharpest was reasoning over rules and prices written in its prompt. Asked for "next Thursday" at the auto shop, it worked out the calendar date, said "November 26th is Thanksgiving, so I can't confirm an appointment that day," and offered the holiday callback its instructions required. When a caller pressed on a diagnostic fee—"the hundred twenty-nine comes off the bill, right? Most shops do that."—it held firm: "it's not waived or credited."

Better yet, it handled live menu math. Before ordering at the pizza shop, a caller asked what a multi-item order with extra toppings and drinks would cost before tax. Working purely from the menu prices in its instructions, with no calculator or external tool, the agent totaled the order on the spot:

Where that leaves 1.1 #

Lower latency and tighter script adherence make a real difference on a live phone line, and most of our trap-heavy calls finished without a hitch. Even so, phone intake is unforgiving of the mistakes that remain: an agent that fumbles spelled surnames, invents a digit in a callback number, or re-asks what the caller just said still needs guardrails where exact details matter.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/gpt-live-1-1-is-fast…] indexed:0 read:4min 2026-11-19 · —