Training Kimi K2.7 on 1,465 GDP.pdf tasks lifts GDPval too, study finds
echen · x · 2026-09-30
New research from echen's team investigates whether training on the underlying skills of GDP.pdf — now a widely used frontier eval — yields fundamental capability gains or just better PDF scores:
- They post-trained Kimi K2.7 on 1,465 GDP.pdf companion tasks.
- GDP.pdf scores improved substantially, from 11.0% to 24.5%.
- Crucially, full-task success on GDPval also improved, showing the gains transfer to broader real-economy task ability rather than merely fitting the eval format.
Paper and blog post are both available.
Related event: Kimi Research: Training on 1,465 PDF Tasks Doubles General Capability(2 posts)→
More from Research
- HCOMP 2026 Honorable Mention: Bayesian cascade analysis of AI credibility indicators — windx0303 · 2026-09-30
- RuneScape Bench Turns an Open-Source MMO Into a Multi-Agent Testbed for LLM Agents — mrdrozdov · 2026-09-30
- New paper: mechanism design could have prevented the Hugging Face incident — joshgans · 2026-09-30
- Multi-Agent System With 4-Layer Memory Learns Procedural Rules From Its Own Resolutions — yashghotekar · 2026-09-30
- Using AI to visualize K-means in action for quantization in an ML course — marc_lelarge · 2026-09-30
- Phonon-2: 164MB open-weights ASR beats Whisper Large at 1/10th the size — julianweisser · 2026-09-30