LIVE / FASCIA Capability Index / Q2 2026 baseline / Last update —

Capability.

A live tracker of frontier AI progress across the six dimensions that compose the path to ASI. Reasoning, autonomy, multimodal, planning, alignment, composability. Calibrated quarterly against a reference benchmark suite and a 30-expert review panel. Open methodology. Adopt it.

Frontier mean
53.0
↑ +7.4 YoY
Composed (5-agent)
67.0
↑ +14.0 over frontier
ASI threshold
95+
All six dimensions
Distance
42.0
Points to ASI
● Live radar Q2 2026 · Indexed 0–100
Overlay frontier mean for comparison
● Frontier Mean

All frontier models.

53.0 / 100 aggregate Frontier
ASI Threshold

95+ on all six dimensions through composition. The frontier sits 42 points away on aggregate — with the largest gaps in autonomy horizon and long-range planning. Composed networks have already crossed 78 on composability and 67 on alignment, suggesting the path forward is architectural, not scale.

Q2 2026 · Full baseline

Every frontier model, every dimension.

Published openly under CC BY 4.0. Any lab may adopt this protocol for internal benchmarking. Replication corrections welcome at support@fasciaai.com.

Model Reasoning Autonomy Multimodal Planning Alignment Composability Aggregate
GPT-5 (Sep 2025)67.140.274.544.357.249.855.5
Claude 4 Opus65.842.169.345.861.050.255.7
Gemini 3 Ultra63.436.773.940.253.446.552.4
Llama-4 405B (Open)58.932.065.836.148.543.247.4
Frontier mean64.238.471.142.054.847.953.0
Composed (5-agent)69.256.372.458.167.578.467.0
Capability Index Pro · Enterprise subscription

Get the full dataset.

Quarterly benchmark data, per-model breakdowns across all 240+ benchmark tasks, reviewer panel annotations, 60-day early access to forthcoming volumes, and a private channel to the research team. For frontier labs, AI VCs, F500 CIOs.

Open methodology stays free · Pro adds the data
How this is built. 6 dimensions, scored 0–100 against a reference benchmark suite of 50–200 tasks per dimension. Calibrated quarterly against a 30-reviewer panel (12 industry, 12 academia, 6 policy). Inter-rater reliability (Krippendorff's α): 0.81 aggregate. Methodology: Vol II — FASCIA Capability Index. Open access under CC BY 4.0. Cite: Fascia Research (2026). FASCIA Capability Index, Vol II. fasciaai.com/capability-index