Claude Fable 5 vs Grok 4.6

Claude Fable 5 (Anthropic) and Grok 4.6 (xAI) compared on price, context window, speed and independent benchmarks. Claude Fable 5 scores higher on the Artificial Analysis Intelligence Index (62.1 vs 60.9), while Grok 4.6 is 6.7× cheaper on a blended basis. Pick Claude Fable 5 for the hardest tasks and Grok 4.6 when cost dominates.

Claude Fable 5Grok 4.6
ProviderAnthropicxAI
Input $/1M$10.0$2.00
Output $/1M$50.0$6.00
Blended $/1M (3:1)$20.0$3.00
Cached input $/1M$1.00$0.50
Context window1M500K
Knowledge cutoff2026-012026-02
Licenseproprietaryproprietary
Speed (tok/s)6860
Artificial Analysis Intelligence Index62.160.9
LMArena Elo14941444
GPQA Diamond92.6%94.9%
AIME99.7%*
SWE-bench Verified95%
MMLU-Pro91.5%*
Humanity's Last Exam55.5%42.9%

← Interactive comparison (pick any 4 models)