Muse Spark 1.3 jumps on Intelligence Index, with agentic evals driving gains at $0.55 per task
ArtificialAnlys · x · 2026-09-03
Artificial Analysis detailed Muse Spark 1.3's gains over 1.2 on the Intelligence Index, concentrated in agentic evaluations: GDPval-AA v2 +94/+139 Elo (1615 to 1709/1754), Terminal-Bench 2.1 up to 85%/86%, and Tau3-Bench Banking from 35% to 47%/52% for xhigh/max.
Minor regressions: both drop 4 points on AA-LCR (83% to 79%); AA-Omniscience accuracy falls 3 points for xhigh (45% to 42%) and 1 point for max (45% to 44%).
Cost efficiency: xhigh is the most cost-efficient at its intelligence level at $0.55 per task under unchanged $1.25/$4.25 per 1M token pricing, undercutting Gemini 3.8 Flash ($0.58), GPT-5.6 Sol ($0.63), GLM-5.3 ($0.68), and same-score peer Grok 4.6 ($0.94).
Related event: Muse Spark 1.3 Gains Intelligence While Leading Cost Efficiency(2 posts)→
More from Models
- GPT-6 'Astra' expected tomorrow: codename spotted in API, rumored 4x GPT-5.6 Sol — daniel_mac8 · 2026-09-03
- Greg Brockman appears to confirm o1, o3 and GPT-5 all built on the GPT-4o base model — flowersslop · 2026-09-03
- Heavy user says GPT-5.3's instruction following is OpenAI's special sauce over Claude — brandon_galang · 2026-09-03
- Early user test: Muse Spark 1.3 oneshots a full website frontend — alexandr_wang · 2026-09-03
- Researcher: Looped Transformers add no real recurrence, just tied-parameter depth — savvyRL · 2026-09-03
- Muse Spark 1.3 lands on OpenCode Zen for free, CEO urges devs to try it — alexandr_wang · 2026-09-03