AVI Variant Impact Score Matches SOTA on Benchmarks, Though Evals Are Biased
anshulkundaje · x · 2026-09-18
In a long thread, Stanford professor Anshul Kundaje assesses the AVI (AlphaGenome Variant Impact) score from the AlphaGenome team. He notes AVI is very competitive with SOTA variant prioritization scores across established rare- and common-variant benchmarks — marginally better in some cases, substantially better in others. He cautions that these widely used evals carry biases and don't fully reveal each method's strengths and limits, but says AVI is not fundamentally flawed.
More from Research
- Xiaomi MiMo's CodeSpecWeave trains coding agents on interdependent specs for long-horizon coding — XiaomiMiMo · 2026-11-02
- Mistral Large 4 writes a quantum chemistry SCF solver from scratch with one short prompt — MistralAI · 2026-11-02
- Hunting for the most concrete "curing cancer with AI" roadmap of 2025 — iskander · 2026-11-02
- New theory paper proves linear decay is the unique minimax-optimal stepsize schedule for SGD — konstmish · 2026-11-02
- Karpathy's nanochat: the best ChatGPT $100 can buy, near 60k GitHub stars — karpathy · 2026-11-02
- After reading 46 resources on agent evals, one author explains why her 95% score was misleading — blaizedsouza · 2026-11-02