Epoch Capabilities Index
PulseAugur coverage of Epoch Capabilities Index — every cluster mentioning Epoch Capabilities Index across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Gemini 4 Argon matches Fable 5.1 on ECI benchmark, trails Opus 5.5 and GPT-6 Astra
Google's Gemini 4 Argon has achieved a score of 165 on the Epoch Capabilities Index (ECI), matching Fable 5.1's performance. This represents a significant improvement from its predecessor, Gemini 3.8 Flash, which scored…
-
Most expensive AI models not the smartest, analysis finds · 2 sources tracked
A recent analysis comparing the capabilities and API prices of 23 large language models reveals that the most expensive models are not necessarily the smartest. The Epoch Capabilities Index (ECI) was used to score model…
-
AIRO system forecasts catastrophic risks using ensemble of frontier LLMs
The Forecasting Research Institute has launched Automated AI Risk Outlook (AIRO), a system that uses an ensemble of leading AI models to forecast the probability of catastrophic risk events. AIRO currently estimates a 0…
-
Anthropic launches Claude Opus 5, challenging Fable 5 on benchmarks
Anthropic has launched Claude Opus 5, a new frontier model that offers performance close to Claude Fable 5 at a reduced cost. Early evaluations show Opus 5 excelling in coding and knowledge work, setting new state-of-th…
-
Meta shifts from open-weight AI, frontier moves to China
Meta, a key player in open-weight LLMs, has shifted its focus away from releasing open models, with its last public releases being Llama 4 Scout and Maverick in April 2025. The company's more recent frontier model, Muse…