Astra leads on reasoning and math, Fable 5.1 still king of coding, says dev after OpenAI pushback
shyamalanadkat · x · 2026-09-04
After Bindi Reddy claimed "OpenAI says Astra completely destroys Fable 5.1," OpenAI DevRel lead Shyamal Anadkat asked what that read was based on. Reddy then offered a more measured take: Astra beats Fable 5.1 on reasoning, math, data analysis, and research, but Fable 5.1 remains the king of coding.
Related event: OpenAI launches flagship GPT-6 Astra to rave reviews and pricing debates(190 posts)→
More from Models
- Opus 5.5 tops OpenRouter spending in 20 of 29 task categories — mmurph · 2026-10-21
- Meta team builds open-source 30B LLM from scratch in months, hails 'second era' — TimDarcet · 2026-10-21
- DFlash drafter for Muse Glimmer-30B: 5 layers, blockwise 16-token spec decoding — TimDarcet · 2026-10-21
- EvoPress quantization shrinks 30B model from 56GB to 19GB at near-bf16 accuracy — TimDarcet · 2026-10-21
- Radar chart: Muse Glimmer-30B benchmarked against Gemma4-31B and Qwen3.6-27B — TimDarcet · 2026-10-21
- Privacy evals: Muse Glimmer-30B leaks less than Qwen3.6-27B on CIMemories — TimDarcet · 2026-10-21