Performance of AI models
On 10 November 2026, Claude Fable 5.2 (Anthropic) has the highest index measured by Epoch AI, 174.2; 5 models, including GPT-6 Astra (169.2), cannot be told apart from it.
General intelligence index of the top 15 AI models
Epoch Capabilities Index (ECI) and its 95% interval, models released in 2026; data as of 10/11/2026
Dot: the measured valueLine: the 95% intervalBand: the interval of the 1st; 5 models (solid dot) cannot be told apart from the 1st
Source: Epoch AI, "Capabilities & benchmarking", ECI index. CC BY 4.0 licence.
The ECI combines dozens of tests into a single index, calculated for models released in 2026. Two models whose 95% intervals overlap cannot be told apart.
Continue in the ranking
The full ranking →
ModelAnthropicClaude Fable 5.21stout of 71 on general intelligence1st on general intelligence: its rank in each benchmark, its settings, its assistants.The entry →RankingAI modelsAll models measured89models measured, of which 42 with an entryOne row per model, its rank in each benchmark, sorting by column, filtering by company.The table →Ranking10 AI assistantsRanking of AI assistants74of 100 for Claude, 1stThe Celsius score: one third performance, one third ethics, one third environment.The ranking →The hub newsletter
This month's ranking, news on the impact of AI and one figure from the AI Impact Database. One newsletter a month at most, free of charge. Past issues
