FLock's THIS/THAT 1.2 decision model beats Claude Opus 5 and GPT-5.6 with one forward pass
matlabulous · x · 2026-09-24
FLock released THIS/THAT Model 1.2, a small model purpose-built for binary decisions. On its 1,710-question public benchmark it scored 87.8%, ahead of Claude Opus 5 (83.4%) and GPT-5.6 (81.6%).
- Answers in a single forward pass with zero generated tokens; latency on an RTX 5080 laptop GPU dropped from 50.3ms to 31.4ms
- Accuracy improved from 77.5% (v1.1) to 87.8%
- Handles exclusion-style rule phrasings at 98-100% across 11 variants
It's pitched as a way to offload millions of micro-decisions from agents. Free on the FLock API platform.
Related event: FLock's THIS/THAT 1.2 small decision model outperforms Opus and GPT(2 posts)→
More from coding & agent
- KAIST's WikiTrace: evidence-linked memory fixes agent "memory-induced degradation" — dair_ai · 2026-11-11
- Why inference speed will be AI products' biggest competitive edge in 1–2 years — itsOmSarraf_ · 2026-11-11
- What happened when I moved vector retrieval into Snowflake SQL instead of orchestrating RAG outside — dima806_dima · 2026-11-11
- OpenAI engineer runs Codex for 26 days straight hunting Atlantis, spawning "vibe archaeology" — Polymarket · 2026-11-11
- He replaced a $5,000/month ghostwriter with 11 Claude Skills and earned $47,000 from one post — aryanXmahajan · 2026-11-11
- Refero Styles ships 2,000+ DESIGN.md files to give Claude Code real design taste — bbssppllvv · 2026-11-11