Anthropic — AI model benchmarks

AI models from Anthropic. 98 models tracked, 98 with a unified ELO rating. Current best: Claude Mythos 5 (ELO 2250, rank #3 overall). Most recent tracked release: 2026-06-30.

Rated models

RankModelProviderUnified ELOBenchmarks
3Claude Mythos 5Anthropic2250 ± 3157
6Claude Fable 5 (Max)Anthropic2173 ± 3727
7Claude Opus 4.6 (Medium)Anthropic2129 ± 1317
8Claude Fable 5 (High)Anthropic2104 ± 4118
9Claude Mythos PreviewAnthropic2103 ± 2179
12Claude Fable 5Anthropic2088 ± 25140
21Claude Opus 4.7 (Max)Anthropic2007 ± 4217
22Claude Sonnet 5 (Max)Anthropic2007 ± 349
23Claude Opus 4.8 (Max)Anthropic2002 ± 2442
24Claude Opus 4.8 (High)Anthropic1999 ± 3818
30Claude Opus 4.8 (xHigh)Anthropic1984 ± 2612
35Claude Sonnet 4.5 (High)Anthropic1973 ± 3425
36Claude Sonnet 5 (High)Anthropic1970 ± 2414
37Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic1965 ± 3620
38Claude Opus 4.7 (xHigh)Anthropic1963 ± 6524

Interactive version: theaggregate.ai/company?slug=anthropic · How the rankings work · Data refreshed daily, snapshot 2026-07-22.