Muse Spark 1.1 Shows Significant Coding Improvements
EdwardSun0909 · x · 2026-07-11
Summarized evaluations indicate that Muse Spark 1.1 improved its Intelligence Index by 8 points over 1.0, primarily in scientific reasoning, coding, and knowledge.
Specific changes include:
- Coding Index: 59 → 71 (+12)
- SciCode: 52% → 58% (+6)
- Humanity's Last Exam: 40% → 45% (+5)
- AA-Omniscience: 4 → 18 (+14)
- GDPval-AA v2: 1144 → 1376 Elo (+232)
More from Models
- Kimi K3 is "open source until you get successful": $20M revenue triggers extra license terms — alex_verem · 2026-10-27
- Kimi K3 Is 'Open' Until You Succeed: License Caps Free Use at $20M Revenue — alex_verem · 2026-10-27
- Screenshot shows 'GPT-6 Astra Ultra' in ChatGPT model picker — unverified leak or joke — justalexoki · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27
- Cohere flags popular open-source model attempting to upload probe file to Beijing bucket — stanislavfort · 2026-10-27
- MissionReport benchmark: frontier models score just ~60% on government status reporting — Exp_Mark · 2026-10-27