GPT-6 Astra Tops ValsAI Code Migration Benchmark at 68% Accuracy, 2-4x Faster
sandersted · x · 2026-09-04
Eval firm ValsAI reports that GPT-6 Astra set a new record on its Code Migration benchmark, ranking #1 with 68% accuracy — a 10-point lead over the second-place model. Astra is also 2-4x faster than comparable models in the comparison.
More from Models
- GPT-6 Astra skips CoT yet still answers correctly, sparking debate on CoT's privileged status — Dan_Jeffries1 · 2026-09-04
- Astra solves Excel World Championship cases ~4x faster than human champions using pure computer use — sandersted · 2026-09-04
- Researcher argues harness and MCP will be absorbed into models — data is the only wall — A_K_Nain · 2026-09-04
- Polymarket opens betting on next Grok model (4.7+) release, odds point to mid-September — Polymarket · 2026-09-04
- Ex-Google DeepMind researcher denny_zhou reveals move to Meta, worked on Muse Spark 1.1-1.3 — infoxiao · 2026-09-04
- The Real AGI Benchmark: Models Still Can't Do Data Science — max_paperclips · 2026-09-04