gemini 3.5 pro leak: what we know and how x users are testing it
Nick Trenkler
7 min read
AI Models & LLM News: Releases, Benchmarks, Comparisons
New models, benchmarks and our tests
Nick Trenkler
7 min read
deepseek v4 flash tops 8 of 11 coding languages on openrouter
Nick Trenkler
1 min read
fable 5 scored 0.97 similarity to kimi – and the proof got deleted
Nick Trenkler
1 min read
fable 5 flash: we tested 5 prompts, got zero usable outputs
Nick Trenkler
1 min read
four models, three canvas tasks: sonnet 5 does more with less
Nick Trenkler
2 min read
meituan's stealth model exposed: longcat vs qwen in 3 coding tasks
Addy Crezee
1 min read
350m vs 685b: liquid ai's tiny phone model takes on deepseek v3
Nick Trenkler
1 min read
baidu unlimited-ocr meets claude opus 4.8: 1998 scan, clean table
Nick Trenkler
1 min read
we tested sakana fugu: 4 builds, zero retries, one prompt each
Addy Crezee
1 min read
4 versions of glm, same 3 prompts – each one beat the last
Nick Trenkler
1 min read
liquid ai ships two tiny search models beating rivals twice their size
Nick Trenkler
2 min read
glm 5.2 beats opus 4.8 as chinese labs sweep hugging face
Addy Crezee
1 min read