AI models / Compare
GPT-6.1 Terra vs LFM3: which delivered after 7 days?
Neither has a verdict yet: both are stamped Too early, with fewer than about five solid user reports each.
| GPT-6.1 Terra | LFM3 | |
|---|---|---|
| Verdict | Too early | Too early |
| Claims held | 3 | 2 |
| Claims mixed | 0 | 0 |
| Claims failed | 1 | 0 |
| Claims unclear | 0 | 1 |
| User reports | 2 | 6 |
| Launched | 26 Oct 2026 | 27 Oct 2026 |
| Last stamped | 30 Oct 2026 | 30 Oct 2026 |
No. 011 · OpenAI
GPT-6.1 Terra
Day 4 of 7Cheap and the coding gain is real, but independent timing finds it about 15 to 25% faster than Sol, nowhere near 3x.
- Launched
- 26 Oct 2026
- Stamped
- 30 Oct 2026
- Claims
- ✓3 held · ~0 mixed · ✗1 failed · ?0 unclear
- Reports
- 2 (0 praise · 0 problem · 2 mixed)
What they claimed
“At max effort, Terra is over three times as token efficient as Claude Opus 5.5, and one-fourth its price per token, resulting in a ~9x lower cost per task.”✓ Holds
“Terra is also much quicker, completing tasks over three times faster than both GPT-6 Astra and GPT-6.1 Sol.”✗ Fails
“At maximum reasoning effort, GPT‑6.1 Terra solves 50.3% of tasks, more than double GPT‑5.6 Terra’s published score of 21.5%.”✓ Holds
“Standard API pricing is $1 per million input tokens, $0.05 per million cached input tokens, and $5 per million output tokens.”✓ Holds
No. 013 · Liquid AI
LFM3
Day 3 of 7It is as small and long-context as promised, but every comparison with the previous model is still Liquid's own, and one hands-on test found it fails coding and multi-step tasks.
- Launched
- 27 Oct 2026
- Stamped
- 30 Oct 2026
- Claims
- ✓2 held · ~0 mixed · ✗0 failed · ?1 unclear
- Reports
- 6 (0 praise · 1 problem · 5 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.”? Unclear
“the text model fits in about 1 GB at 4-bit precision.”✓ Holds
“256K context window for the text model.”✓ Holds
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
Weekly email · Fridays 14:00 CEST
Get the Friday Receipt
Every Friday: the week’s new day 7 receipts, the ones we re-stamped, and any corrections. One email, no sponsors from companies we review.
Prefer not to give an email? Follow the RSS feed or @day7dev on X.