18-Model AI Research Experiment: Fable 5 Closes 82% of Human Gap
eliebakouch · x · 2026-08-16
Prime Intellect ran the largest open experiment on autonomous AI research, executing 153 runs across 18 frontier models on the nanoGPT optimizer track. Using 8xH200s per run for up to 8 days, this dwarfs similar internal benchmarks by OpenAI and Anthropic which ran for less than a day. Results show a significant performance gap between models: Fable 5 closed 82% of the gap to the human record, with Kimi K3 also performing impressively. While no fundamentally new methods were discovered—winning ingredients were combinations of existing literature—the experiment highlights differences in how models approach experimental design and execution.
More from coding & agent
- Coding agents keep opening 3 stacked PRs per chat, and merging them is a nightmare — holdenmatt · 2026-10-16
- Google-led paper uses sequential auctions to organize decentralized LLM agent workflows — _onionesque · 2026-10-16
- Since OpenAI's math release, GitHub contributors keep driving down the integer-multiplication kappa — xennygrimmato_ · 2026-10-16
- Pattern MCP makes coding agents check existing components before writing new code — DonR954 · 2026-10-16
- Zero-keyframe procedural spider walks walls and ceilings using pure raycasts — yshan2u · 2026-10-16
- OpenCode v1.19.2 keeps 1.x installs off the 2.x update path — opencode-agent[bot] · 2026-10-16