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

Kimi K3.1 Pro vs LFM3: which delivered after 7 days?

Same stamp after day 7: both Kimi K3.1 Pro and LFM3 are stamped Delivered. The claim tallies below show where each one held and where it didn't.

Kimi K3.1 ProLFM3
VerdictDeliveredDelivered
Claims held22
Claims mixed11
Claims failed00
Claims unclear10
User reports78
Launched23 Oct 202627 Oct 2026
Last stamped7 Nov 202613 Nov 2026

No. 027 · Moonshot AI

Kimi K3.1 Pro

DeliveredDay 7 verdict

Weights landed on time and it ranks near the top, but vendor-harness scores shrink in independent runs and it is slow.

Launched
23 Oct 2026
Stamped
7 Nov 2026
Claims
✓2 held · ~1 mixed · ✗0 failed · ?1 unclear
Reports
7 (3 praise · 2 problem · 2 mixed)

What they claimed

“Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed are available today on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API. The full model weights will be released by Nov 4.”
✓ Holds
“our most capable 3T-class open-weight model to date, with a 1-million-token context window”
✓ Holds
“K3.1 Pro scores 65.7%, ahead of GPT-6 Astra (58.2%) and narrowly behind Claude Opus 5.5 (66.4%)”
~ Mixed
“Kimi K3.1 Pro Highspeed, which delivers 2-3× the speed of K3.1 Pro for more responsive interactions”
? Unclear

Full receipt

No. 013 · Liquid AI

LFM3

DeliveredDay 7 verdict

Tiny, local and long-context exactly as promised; the 'beats our bigger model' line is still Liquid's own, and it fails at coding.

Launched
27 Oct 2026
Stamped
13 Nov 2026
Claims
✓2 held · ~1 mixed · ✗0 failed · ?0 unclear
Reports
8 (1 praise · 1 problem · 6 mixed)

What they claimed

“a new tri-hybrid architecture and training recipe allow LFM3-1.7B to outperform our previous LFM2.5-2.6B while using 35% fewer parameters.”
~ Mixed
“the text model fits in about 1 GB at 4-bit precision.”
✓ Holds
“256K context window for the text model.”
✓ Holds

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