Leaderboard: Fable 5 Tops Autonomous Research, Kimi K3 Follows
eliebakouch · x · 2026-08-16
Prime Intellect released the leaderboard for the autonomous NanoGPT optimizer speedrun. Among the 18 models tested, Fable 5 ranked first with 2,726 steps, closing 81.7% of the performance gap to the human record. Opus 5 and Kimi K3 took second and third place, respectively, both closing over 50% of the gap. GPT-5.6 series models showed mid-tier performance, ranking lower. Several models, including Qwen 3.8 Max and DeepSeek V4 Pro, are still listed as running.
More from coding & agent
- Devs say LLM coding mistakes are a different class: overcomplication, inferred limits, worse at higher reasoning — Mu5_ · 2026-10-16
- How do you debug bad agent runs when you already have tracing? — Sensitive-Parsnip-12 · 2026-10-16
- Where does pre-task context live for agents? Devs debate workflows beyond handoff — shishen2026 · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- CODESTRUCT reframes codebases as AST action spaces to fix brittle LLM code agents — burkov · 2026-10-16
- Would you install another SDK for agent debugging on top of your tracing stack? — Sensitive-Parsnip-12 · 2026-10-16