Day 7 · 2026-11-17
35 launches checked147 claims quoted word for word179 user reports linked10 verified fixes linked40 corrections publishedLive 25 days5 of 5 founding sponsor spots left
AI launches, checked against real usersLast re-stamped 17 Nov 2026

AI models / Compare

Claude Opus 5.5 vs Gemini 4 Carbon: which delivered after 7 days?

Same stamp after day 7: both Claude Opus 5.5 and Gemini 4 Carbon are stamped Delivered. The claim tallies below show where each one held and where it didn't.

Claude Opus 5.5Gemini 4 Carbon
VerdictDeliveredDelivered
Claims held22
Claims mixed20
Claims failed00
Claims unclear11
User reports101
Launched22 Sept 202628 Oct 2026
Last stamped30 Oct 202613 Nov 2026

No. 002 · Anthropic

Claude Opus 5.5

DeliveredDay 7 verdict

The 20% price cut and 30% speed-up check out, and Epoch and Agent Arena put it at Fable level. It uses more tokens, so cost per task isn't 40% lower.

Launched
22 Sept 2026
Stamped
30 Oct 2026
Claims
✓2 held · ~2 mixed · ✗0 failed · ?1 unclear
Reports
10 (2 praise · 7 problem · 1 mixed)

What they claimed

“It performs at the level of Claude Fable 5.1 on most work and costs 40% less to run than Opus 5.”
~ Mixed
“Input and output tokens are $4 and $20 per million, 20% less than Opus 5.”
✓ Holds
“In addition to the price drop, we’re increasing five-hour usage limits on Pro, Max, Team, and seat-based Enterprise plans.”
~ Mixed
“It is much less likely than recent models to take hard-to-reverse actions or act outside the boundaries it’s been given”
? Unclear
“Opus 5.5 also generates output more than 30% faster than Opus 5.”
✓ Holds

Full receipt

No. 014 · Google DeepMind

Gemini 4 Carbon

DeliveredDay 7 verdict

It did top the independent index at launch and opened to everyone two weeks later; the cyber scores are still Google's own runs.

Launched
28 Oct 2026
Stamped
13 Nov 2026
Claims
✓2 held · ~0 mixed · ✗0 failed · ?1 unclear
Reports
1 (0 praise · 0 problem · 1 mixed)

What they claimed

“Carbon ranks #1 on the recently updated v5.0 of Artificial Analysis Intelligence Index at 59.”
✓ Holds
“Starting this week, we will make Carbon available to a subset of cyber defenders”
✓ Holds
“landing a firm lead in SEC-bench Pro (88.2%) for finding vulnerabilities”
? Unclear

Full receipt

Both stamps come from the public user reports linked on each receipt, under the same method. Verdicts are opinion and are never paid for.

Keep comparingall AI models